Version: 0.4.7
Date: 2025-09-03
Title: Data Sets for Econometrics
Author: Yves Croissant [aut], Spencer Graves [aut, cre, ctb]
Maintainer: Spencer Graves <spencer.graves@effectivedefense.org>
BugReports: https://github.com/sbgraves237/Ecdat/issues
Depends: R (≥ 3.5.0)
Suggests: Ecfun, plm, systemfit, carData, wooldridge
Description: Data sets for econometrics, including political science.
LazyData: true
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
Language: en-us
URL: https://www.r-project.org
NeedsCompilation: no
Packaged: 2025-09-03 21:51:22 UTC; sg
Repository: CRAN
Date/Publication: 2025-09-04 07:50:02 UTC

ACLED countries and codes with population and GDP

Description

Countries and codes used by the Armed Conflict Location and Event Data project with population and Gross Domestic Project (GDP) numbers for recent years. Population and GDP data are from the World Bank when available and from other sources otherwise. When no World Bank data are available, numbers may be reported from the closest year conveniently available, as noted in Comments; in those cases, the data may not be as accurate as the numbers from the World Bank.

NOTE: This code will be offered to the maintainer of the acled.api package. If they like it, it may not stay in Ecdat.

Usage

data(ACLEDpopGDP)

Format

A dataframe with rownames = ACLEDcountry containing :

ACLEDcountry

A character vector of the country names used by ACLED in the monthly totals of events and deaths between 2021-01 and 2024-09 extracted 2024-10-24.

ISO3

3-character ISO 3166-1 code for Country.

WBcountry

A character vector of the country names used by the World Bank (WB) in data extracted 2024-11-06.

pop2020, pop2021, pop2022, pop2023, pop, GDPpcn2020, GDPpcn2021, GDPpcn2022, GDPpcn2023, GDPpcn, GDPpcp2020, GDPpcp2021, GDPpcp2022, GDPpcp2023, GDPpcp

World Bank population and nominal Gross Domestic Product per capita (GDPpc) in constant 2015 US$ plus GDP per capita, PPP (constant 2021 international $) extracted 2024-11-13 for the indicated years unless otherwise specified in "Comments". For country subdivisions like Jersey, the World Bank extract used did not include such numbers. For those "countries", numbers were taken from Wikipedia and assigned to the nearest year in the 2020:2023 range and noted in "Comments".

Comments

Blank (”) if the data is from the World Bank. Otherwise, this lists the source of the population and GDP data, the applicable year, and other anomalies.

Source

ACLED Explorer was used 2024-10-24 to download monthly totals between 2021-01 and 2024-09 of events and death in two files: one for events and another for deaths. Both had data on 234 "countries", though some were actually subdivisions. For example, ACLED "countries" includes the "Bailiwick of Jersey", which is a "British Crown" dependency, and the World Bank does not provide data on them as they do on sovereign countries.

However, the country names used by ACLED Explorer do not match the country names used by the World Bank.

This ACLEDpopGDP data.frame was created to facilitate merging ACLED data with data on population and GDP ... from the World Bank when available and from other sources when not.

I got most of the ISO 3166-1 3-character country codes using grepInTable. That function was NOT able to find country codes for the Caribbean Netherlands, Christmas Island, eSwatini, and North Macedonia, which have 3-letter ISO 3166-1 codes of BES, CXR, SWZ, and MKD, respectively.

From the World Bank website, I got something by clicking DataBank. From there, I clicked on "Population, total". This displayed numbers by country and year from 2008 to 2015. I clicked, "Add Time". From there I clicked "Unselect all" then selected 2020, 2021, 2022, and 2023. Then I clicked "x" in the upper right and "Apply Changes".

Then I clicked "Add Series". From there I found that many series I did not want were selected, so I clicked "Unselect all", then selected "GDP (constant 2015 US$)" and "Population, total". Then I clicked "x" in the upper right and "Apply Changes" as before.

Then I clicked "Download options" and selected "Excel". That downloaded a file named 'P_Popular Indicators.xlsx', which I moved to the working directory, read into R and merged in the obvious way to create most of ACLEDpopGDP.

For "Countries" not in the World Bank data I extracted, I got numbers from relevant Wikipedia articles and documented the source in ACLEDpopGDP[, "Comments"].

References

Armed Conflict Location and Event Data

DataBank

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Examples

# Country in World Bank data
ACLEDpopGDP['China', ]

# Country NOT in World Bank data
ACLEDpopGDP['Taiwan', ]

# Partial matching works if unique
ACLEDpopGDP['Czech',]

# Partial matching does NOT work if not unique
ACLEDpopGDP['Saint', ]
# Instead use, e.g., grep
ACLEDpopGDP[grep('Saint', ACLEDpopGDP[, 'ACLEDcountry']), ]

# If you know the ISO 3166-1 3-letter code:
ACLEDpopGDP['CPV'==ACLEDpopGDP[, 'ISO3'], ]
# NOTE: In this example, ACLEDcountry != 
# WBcountry.  

# No NAs in pop

all.equal(length(which(is.na(ACLEDpopGDP$pop))), 0)


# Only one NA in GDPpcn and GDPpcp: 
(GDPpNA <- which(is.na(ACLEDpopGDP$GDPpcp)))
(GDPnNA <- which(is.na(ACLEDpopGDP$GDPpcn)))
# Antarctica: 

all.equal(ACLEDpopGDP$ACLEDcountry[GDPpNA], 'Antarctica')



ACLEDpopGDP[c('China', 'India'), ]

Ship Accidents

Description

a cross-section

number of observations : 40

Usage

data(Accident)

Format

A dataframe containing :

type

ship type, a factor with levels (A,B,C,D,E)

constr

year constructed, a factor with levels (C6064,C6569,C7074,C7579)

operate

year operated, a factor with levels (O6074,O7579)

months

measure of service amount

acc

accidents

Source

McCullagh, P. and J. Nelder (1983) Generalized Linear Models, New York:Chapman and Hall.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F21.3.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Accountants and Auditors in the US 1850-2016

Description

Accountants and auditors as a percent of the US labor force 1850 to 2016 updating the analysis in Wyatt and Hecker (2006).

Usage

data(AccountantsAuditorsPct)

Format

a numeric vector of length 30 giving the percent of the US labor force in "Accounting and Auditing" each decade from 1850 to 2010 except for 1940 plus each year between 2011 and 2016.

Source

This is based primarily on data extracted from the Integrated Public Use Microdata Series on 2018-09-01 with the computations documented in a vignette by this title in the Ecfun package.

This updates the data on Accountants and Auditors in Wyatt and Hecker (2006). They relied primarily on data extracted from the Integrated Public Use Microdata Series. This follows the same methodology with two modifications:

1. IPUMS provided no data for 1940. Wyatt and Hecker (2006) used Historical Statistics of the United States, Colonial Times to 1970, Bicentennial Edition, part 1 (U.S. Department of Commerce, Bureau of the Census, 1975) for 1910-1940. The current data set uses that source only for 1040.

2. The IPUMS numbers showed an extreme jump from 1850 to 1860 followed by an even more extreme drop to 1870. The numbers in Sobek (2006) showed essentially the same behavior. Specifically, Sobek (2006) estimated the number of accountants and auditors in the US in those three years as 700, 1700, and 1200, and the labor force as 5277000, 8160800, and 12004200. These numbers give accountants and auditors as 0.013, 0.021, and 0.010 percent of the labor force, respectively for those three years. These numbers portray an incredible increase in the employment of accountants and auditors between 1850 and 1860 followed by a shocking decline the following decade. If, however, we swap the 1700 and 1200 between 1860 and 1870, the percentages become quite stable: 0.013, 0.015, and 0.014 percent, respectively.

We use these latter numbers, even though the uncorrected numbers seem more consistent with the numbers obtained from IPUMS.

References

Historical Statistics of the United States, Colonial Times to 1970, Bicentennial Edition, part 1 (U.S. Department of Commerce, Bureau of the Census, 1975)

Steven Ruggles, Sarah Flood, Ronald Goeken, Josiah Grover, Erin Meyer, Jose Pacas, and Matthew Sobek (2018) IPUMS USA: Version 8.0 [dataset]. Minneapolis, MN: IPUMS. doi:10.18128/D010.V8.0

Matthew Sobek (2006) Chapter Ba. "Labor Occupations" in Susan B. Carter, ed., Historical Statistics of the United States, Cambridge U. Pr.

Ian D. Wyatt and Daniel E. Hecker (2006) "Occupational changes during the 20th century", Monthly Labor Review, March 2006, pp. 35-57

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Examples

data(AccountantsAuditorsPct)
plot(names(AccountantsAuditorsPct), AccountantsAuditorsPct, 
  type='l', log='y', cex.axis=1.8)
# for the version of this contributed to Wikimedia Commons

Cost for U.S. Airlines

Description

a panel of 6 observations from 1970 to 1984

number of observations : 90

observation : production units

country : United States

Usage

data(Airline)

Format

A dataframe containing :

airline

airline

year

year

cost

total cost, in $1,000

output

output, in revenue passenger miles, index number

pf

fuel price

lf

load factor, the average capacity utilization of the fleet

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F7.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Air Quality for Californian Metropolitan Areas

Description

a cross-section from 1972

number of observations : 30

observation : regional

country : United States

Usage

data(Airq)

Format

A dataframe containing :

airq

indicator of air quality (the lower the better)

vala

value added of companies (in thousands of dollars)

rain

amount of rain (in inches)

coas

is it a coastal area ?

dens

population density (per square mile)

medi

average income per head (in US dollars)

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 4.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Unemployment of Blue Collar Workers

Description

a cross-section from 1972

number of observations : 4877

observation : individuals

country : United States

Usage

data(Benefits)

Format

A time series containing :

stateur

state unemployment rate (in %)

statemb

state maximum benefit level

state

state of residence code

age

age in years

tenure

years of tenure in job lost

joblost

a factor with levels (slack_work,position_abolished,seasonal_job_ended,other)

nwhite

non-white ?

school12

more than 12 years of school ?

sex

a factor with levels (male,female)

bluecol

blue collar worker ?

smsa

lives in SMSA ?

married

married ?

dkids

has kids ?

dykids

has young kids (0-5 yrs) ?

yrdispl

year of job displacement (1982=1,..., 1991=10)

rr

replacement rate

head

is head of household ?

ui

applied for (and received) UI benefits ?

Source

McCall, B.P. (1995) “The impact of unemployment insurance benefit levels on recipiency”, Journal of Business and Economic Statistics, 13, 189–198.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 7.

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Bids Received By U.S. Firms

Description

a cross-section

number of observations : 126

observation : production units

country : United States

Usage

data(Bids)

Format

A dataframe containing :

docno

doc no.

weeks

weeks

numbids

count

takeover

delta (1 if taken over)

bidprem

bid Premium

insthold

institutional holdings

size

size measured in billions

leglrest

legal restructuring

rearest

real restructuring

finrest

financial restructuring

regulatn

regulation

whtknght

white knight

Source

Jaggia, Sanjiv and Satish Thosar (1993) “Multiple Bids as a Consequence of Target Management Resistance”, Review of Quantitative Finance and Accounting, 447–457.

Cameron, A.C. and Per Johansson (1997) “Count Data Regression Models using Series Expansions: with Applications”, Journal of Applied Econometrics, 12, may, 203–223.

References

Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 5.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Budget Share of Food for Spanish Households

Description

a cross-section from 1980

number of observations : 23972

observation : households

country : Spain

Usage

data(BudgetFood)

Format

A dataframe containing :

wfood

percentage of total expenditure which the household has spent on food

totexp

total expenditure of the household

age

age of reference person in the household

size

size of the household

town

size of the town where the household is placed categorized into 5 groups: 1 for small towns, 5 for big ones

sex

sex of reference person (man,woman)

Source

Delgado, A. and Juan Mora (1998) “Testing non–nested semiparametric models : an application to Engel curves specification”, Journal of Applied Econometrics, 13(2), 145–162.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Budget Shares for Italian Households

Description

a cross-section from 1973 to 1992

number of observations : 1729

observation : households

country : Italy

Usage

data(BudgetItaly)

Format

A dataframe containing :

wfood

food share

whouse

housing and fuels share

wmisc

miscellaneous share

pfood

food price

phouse

housing and fuels price

pmisc

miscellaneous price

totexp

total expenditure

year

year

income

income

size

household size

pct

cellule weight

Source

Bollino, Carlo Andrea, Frederico Perali and Nicola Rossi (2000) “Linear household technologies”, Journal of Applied Econometrics, 15(3), 253–274.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Budget Shares of British Households

Description

a cross-section from 1980 to 1982

number of observations : 1519

observation : households

country : United Kingdom

Usage

data(BudgetUK)

Format

A dataframe containing :

wfood

budget share for food expenditure

wfuel

budget share for fuel expenditure

wcloth

budget share for clothing expenditure

walc

budget share for alcohol expenditure

wtrans

budget share for transport expenditure

wother

budget share for other good expenditure

totexp

total household expenditure (rounded to the nearest 10 UK pounds sterling)

income

total net household income (rounded to the nearest 10 UK pounds sterling)

age

age of household head

children

number of children

Source

Blundell, Richard, Alan Duncan and Krishna Pendakur (1998) “Semiparametric estimation and consumer demand”, Journal of Applied Econometrics, 13(5), 435–462.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Wages in Belgium

Description

a cross-section from 1994

number of observations : 1472

observation : individuals

country : Belgium

Usage

data(Bwages)

Format

A dataframe containing :

wage

gross hourly wage rate in euro

educ

education level from 1 [low] to 5 [high]

exper

years of experience

sex

a factor with levels (males,female)

Source

European Community Household Panel.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 3.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Earnings from the Current Population Survey

Description

a cross-section from 1998

number of observations : 11130

observation : individuals

country : United States

Usage

data(CPSch3)

Format

A dataframe containing :

year

survey year

ahe

average hourly earnings

sex

a factor with levels (male,female)

Source

Bureau of labor statistics, U.S. Department of Labor https://www.bls.gov.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 3.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Growth of CRAN

Description

Data casually collected on the number of packages on the Comprehensive R Archive Network (CRAN) at different dates.

NOTE: This could change in the future. See Details below.

Usage

data(CRANpackages)

Format

A data.frame containing:

Version

an ordered factor of the R version number primarily in use at the time. This was taken from archives of the major releases at https://svn.r-project.org/R/branches/R-1-3-patches/tests/internet.Rout.save, ... https://svn.r-project.org/R/branches/R-3-1-branch/tests/internet.Rout.save

Date

an object of class Date giving the date on which the count of the number of CRAN packages was determined.

Packages

an integer number of packages on the CRAN mirror checked on the indicated Date.

Source

A factor giving the source (person) who collected the data.

Details

This seems to provide the most widely available source for data on the growth of CRAN, manually recorded by John Fox and Spencer Graves. For a discussion of these and related data, see Fox (2009).

For more detail, see the CRAN packages data on GitHub maintained by Hadley Wickham. This contains the description file of every package uploaded to CRAN prior to the date of Hadley's most recent update. The current maintainer of the Ecdat and Ecfun packages would consider contributions along the following lines:

1. It might be nice to have a more complete dataset or datasets showing CRAN growth. This might include code fitting multiple models and predicting future growth with error bounds computed using Bayesian Model Averaging. These model fits might make an interesting addition to the examples in this help file. With a little more effort, it might make an interesting note for R Journal. Functions written to fit those models might be added to the Ecfun package.

2. It might be nice to have a function in Ecfun to download the CRAN packages data from GitHub and convert it to a format suitable for updating this dataset.

The current maintainer for Ecdat and Ecfun (Spencer Graves) might be willing to accept code and documentation for this but is not ready to do it himself at the present time.

Source

John Fox, "Aspects of the Social Organization and Trajectory of the R Project", R Journal, 1(2), Dec. 2009, 5-13. https://journal.r-project.org/archive/2009-2/RJournal_2009-2_Fox.pdf, accessed 2014-04-13.

Examples

plot(Packages~Date, CRANpackages, log='y')
# almost exponential growth

Daily Returns from the CRSP Database

Description

daily observations from 1969-1-03 to 1998-12-31

number of observations : 2528

observation : production units

country : United States

Usage

data(CRSPday)

Format

A dataframe containing :

year

the year

month

the month

day

the day

ge

the return for General Electric, PERMNO 12060

ibm

the return for IBM, PERMNO 12490

mobil

the return for Mobil Corporation, PERMNO 15966

crsp

the return for the CRSP value-weighted index, including dividends

Source

Center for Research in Security Prices, Graduate School of Business, University of Chicago, 725 South Wells - Suite 800, Chicago, Illinois 60607, https://www.crsp.org.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 7, 9 and 15.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Monthly Returns from the CRSP Database

Description

monthly observations from 1969-1 to 1998-12

number of observations : 360

observation : production units

country : United States

Usage

data(CRSPmon)

Format

A time series containing :

ge

the return for General Electric, PERMNO 12060

ibm

the return for IBM, PERMNO 12490

mobil

the return for Mobil Corporation, PERMNO 15966

crsp

the return for the CRSP value-weighted index, including dividends

Source

Center for Research in Security Prices, Graduate School of Business, University of Chicago, 725 South Wells - Suite 800, Chicago, Illinois 60607, https://www.crsp.org.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 13.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Stock Market Data

Description

monthly observations from 1960–01 to 2002–12

number of observations : 516

Usage

data(Capm)

Format

A time series containing :

rfood

excess returns food industry

rdur

excess returns durables industry

rcon

excess returns construction industry

rmrf

excess returns market portfolio

rf

risk-free return

Source

most of the above data are from Kenneth French's data library at http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Stated Preferences for Car Choice

Description

a cross-section

number of observations : 4654

observation : individuals

country : United States

Usage

data(Car)

Format

A dataframe containing :

choice

choice of a vehicle among 6 propositions

college

college education ?

hsg2

size of household greater than 2 ?

coml5

commute lower than 5 miles a day ?

typez

body type, one of regcar (regular car), sportuv (sport utility vehicle), sportcar, stwagon (station wagon), truck, van, for each proposition z from 1 to 6

fuelz

fuel for proposition z, one of gasoline, methanol, cng (compressed natural gas), electric.

pricez

price of vehicle divided by the logarithm of income

rangez

hundreds of miles vehicle can travel between refuelings/rechargings

accz

acceleration, tens of seconds required to reach 30 mph from stop

speedz

highest attainable speed in hundreds of mph

pollutionz

tailpipe emissions as fraction of those for new gas vehicle

sizez

0 for a mini, 1 for a subcompact, 2 for a compact and 3 for a mid–size or large vehicle

spacez

fraction of luggage space in comparable new gas vehicle

costz

cost per mile of travel (tens of cents) : home recharging for electric vehicle, station refueling otherwise

stationz

fraction of stations that can refuel/recharge vehicle

Source

McFadden, Daniel and Kenneth Train (2000) “Mixed MNL models for discrete response”, Journal of Applied Econometrics, 15(5), 447–470.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

The California Test Score Data Set

Description

a cross-section from 1998-1999

number of observations : 420

observation : schools

country : United States

Usage

data(Caschool)

Format

A dataframe containing :

distcod

district code

county

county

district

district

grspan

grade span of district

enrltot

total enrollment

teachers

number of teachers

calwpct

percent qualifying for CalWORKS

mealpct

percent qualifying for reduced-price lunch

computer

number of computers

testscr

average test score (read.scr+math.scr)/2

compstu

computer per student

expnstu

expenditure per student

str

student teacher ratio

avginc

district average income

elpct

percent of English learners

readscr

average reading score

mathscr

average math score

Source

California Department of Education https://web.archive.org/web/20250823081216/https://www.cde.ca.gov/.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 4–7.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Choice of Brand for Catsup

Description

a cross-section

number of observations : 2798

observation : individuals

country : United States

Usage

data(Catsup)

Format

A dataframe containing :

id

individuals identifiers

choice

one of heinz41, heinz32, heinz28, hunts32

disp.z

is there a display for brand z ?

feat.z

is there a newspaper feature advertisement for brand z ?

price.z

price of brand z

Source

Jain, Dipak C., Naufel J. Vilcassim and Pradeep K. Chintagunta (1994) “A random–coefficients logit brand–choice model applied to panel data”, Journal of Business and Economics Statistics, 12(3), 317.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Ketchup, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Cigarette Consumption

Description

a panel of 46 observations from 1963 to 1992

number of observations : 1380

observation : regional

country : United States

Usage

data(Cigar)

Format

A dataframe containing :

state

state abbreviation

year

the year

price

price per pack of cigarettes

pop

population

pop16

population above the age of 16

cpi

consumer price index (1983=100)

ndi

per capita disposable income

sales

cigarette sales in packs per capita

pimin

minimum price in adjoining states per pack of cigarettes

Source

Baltagi, B.H. and D. Levin (1992) “Cigarette taxation: raising revenues and reducing consumption”, Structural Changes and Economic Dynamics, 3, 321–335.

Baltagi, B.H., J.M. Griffin and W. Xiong (2000) “To pool or not to pool: homogeneous versus heterogeneous estimators applied to cigarette demand”, Review of Economics and Statistics, 82, 117–126.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

The Cigarette Consumption Panel Data Set

Description

a panel of 48 observations from 1985 to 1995

number of observations : 528

observation : regional

country : United States

Usage

data(Cigarette)

Format

A dataframe containing :

state

state

year

year

cpi

consumer price index

pop

state population

packpc

number of packs per capita

income

state personal income (total, nominal)

tax

average state, federal, and average local excise taxes for fiscal year

avgprs

average price during fiscal year, including sales taxes

taxs

average excise taxes for fiscal year, including sales taxes

Source

Professor Jonathan Gruber, MIT.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 10.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Sales Data of Men's Fashion Stores

Description

a cross-section from 1990

number of observations : 400

observation : production units

country : Netherland

Usage

data(Clothing)

Format

A dataframe containing :

tsales

annual sales in Dutch guilders

sales

sales per square meter

margin

gross-profit-margin

nown

number of owners (managers)

nfull

number of full-timers

npart

number of part-timers

naux

number of helpers (temporary workers)

hoursw

total number of hours worked

hourspw

number of hours worked per worker

inv1

investment in shop-premises

inv2

investment in automation.

ssize

sales floor space of the store (in m$^2$).

start

year start of business

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 3.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Prices of Personal Computers

Description

a cross-section from 1993 to 1995

number of observations : 6259

observation : goods

country : United States

Usage

data(Computers)

Format

A dataframe containing :

price

price in US dollars of 486 PCs

speed

clock speed in MHz

hd

size of hard drive in MB

ram

size of Ram in in MB

screen

size of screen in inches

cd

is a CD-ROM present ?

multi

is a multimedia kit (speakers, sound card) included ?

premium

is the manufacturer was a "premium" firm (IBM, COMPAQ) ?

ads

number of 486 price listings for each month

trend

time trend indicating month starting from January of 1993 to November of 1995.

Source

Stengos, T. and E. Zacharias (2005) “Intertemporal pricing and price discrimination : a semiparametric hedonic analysis of the personal computer market”, Journal of Applied Econometrics, forthcoming.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Quarterly Data on Consumption and Expenditure

Description

quarterly observations from 1947-1 to 1996-4

number of observations : 200

observation : country

country : Canada

Usage

data(Consumption)

Format

A time series containing :

yd

personal disposable income, 1986 dollars

ce

personal consumption expenditure, 1986 dollars

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 1, 3, 4, 6, 9, 10, 14 and 15.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Choice of Brand for Crackers

Description

a cross-section

number of observations : 3292

observation : individuals

country : United States

Usage

data(Cracker)

Format

A dataframe containing :

id

individuals identifiers

choice

one of sunshine, kleebler, nabisco, private

disp.z

is there a display for brand z ?

feat.z

is there a newspaper feature advertisement for brand z ?

price.z

price of brand z

Source

Jain, Dipak C., Naufel J. Vilcassim and Pradeep K. Chintagunta (1994) “A random–coefficients logit brand–choice model applied to panel data”, Journal of Business and Economics Statistics, 12(3), 317.

Paap, R. and Philip Hans Frances (2000) “A dynamic multinomial probit model for brand choices with different short–run effects of marketing mix variables”, Journal of Applied Econometrics, 15(6), 717–744.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Crime in North Carolina

Description

a panel of 90 observations from 1981 to 1987

number of observations : 630

observation : regional

country : United States

Usage

data(Crime)

Format

A dataframe containing :

county

county identifier

year

year from 1981 to 1987

crmrte

crimes committed per person

prbarr

'probability' of arrest

prbconv

'probability' of conviction

prbpris

'probability' of prison sentence

avgsen

average sentence, days

polpc

police per capita

density

hundreds of people per square mile

taxpc

tax revenue per capita

region

one of 'other', 'west' or 'central'

smsa

'yes' or 'no' if in SMSA

pctmin

percentage minority in 1980

wcon

weekly wage in construction

wtuc

weekly wage in trns, util, commun

wtrd

weekly wage in whole sales and retail trade

wfir

weekly wage in finance, insurance and real estate

wser

weekly wage in service industry

wmfg

weekly wage in manufacturing

wfed

weekly wage of federal employees

wsta

weekly wage of state employees

wloc

weekly wage of local governments employees

mix

offense mix: face-to-face/other

pctymle

percentage of young males

Note

Thanks to Yungfong "Frank" Tang for identifying an error in the description of "density", previously documented erroneously as only "people per square mile".

Source

Cornwell, C. and W.N. Trumbull (1994) “Estimating the economic model of crime with panel data”, Review of Economics and Statistics, 76, 360–366.

Baltagi, B. H. (2006) “Estimating an economic model of crime using panel data from North Carolina”, Journal of Applied Econometrics, 21(4), May/June 2006, pp. 543-547.

See also: CRIME4.DES and Baltagi in JAE Data Archive.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series, Crime

DM Dollar Exchange Rate

Description

weekly observations from 1975 to 1989

number of observations : 778

observation : country

country : Germany

Usage

data(DM)

Format

A dataframe containing :

date

the date of the observation (19850104 is January, 4, 1985)

s

the ask price of the dollar in units of DM in the spot market on Friday of the current week

f

the ask price of the dollar in units of DM in the 30-day forward market on Friday of the current week

s30

the bid price of the dollar in units of DM in the spot market on the delivery date on a current forward contract

Source

Bekaert, G. and R. Hodrick (1993) “On biases in the measurement of foreign exchange risk premiums”, Journal of International Money and Finance, 12, 115-138.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 6, 438-443.

See Also

Pound, Yen, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Pricing the C's of Diamond Stones

Description

a cross-section from 2000

number of observations : 308

observation : goods

country : Singapore

Usage

data(Diamond)

Format

A dataframe containing :

carat

weight of diamond stones in carat unit

colour

a factor with levels (D,E,F,G,H,I)

clarity

a factor with levels (IF,VVS1,VVS2,VS1,VS2)

certification

certification body, a factor with levels ( GIA, IGI, HRD)

price

price in Singapore $

Source

Chu, Singfat (2001) “Pricing the C's of Diamond Stones”, Journal of Statistics Education, 9(2).

References

Journal of Statistics Education's data archive : https://jse.amstat.org/jse_data_archive.htm.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Number of Doctor Visits

Description

a cross-section from 1986

number of observations : 485

observation : individuals

country : United States

Usage

data(Doctor)

Format

A dataframe containing :

doctor

the number of doctor visits

children

the number of children in the household

access

is a measure of access to health care

health

a measure of health status (larger positive numbers are associated with poorer health)

Source

Gurmu, Shiferaw (1997) “Semiparametric estimation of hurdle regression models with an application to medicaid utilization”, Journal of Applied Econometrics, 12(3), 225-242.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 11.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

DoctorContacts, DoctorAUS, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Doctor Visits in Australia

Description

a cross-section from 1977–1978

number of observations : 5190

observation : individuals

country : Australia

Usage

data(DoctorAUS)

Format

A dataframe containing :

sex

sex

age

age

income

annual income in tens of thousands of dollars

insurance

insurance contract (medlevy : medibanl levy, levyplus : private health insurance, freepoor : government insurance due to low income, freerepa : government insurance due to old age disability or veteran status

illness

number of illness in past 2 weeks

actdays

number of days of reduced activity in past 2 weeks due to illness or injury

hscore

general health score using Goldberg's method (from 0 to 12)

chcond

chronic condition (np : no problem, la : limiting activity, nla : not limiting activity)

doctorco

number of consultations with a doctor or specialist in the past 2 weeks

nondocco

number of consultations with non-doctor health professionals (chemist, optician, physiotherapist, social worker, district community nurse, chiropodist or chiropractor) in the past 2 weeks

hospadmi

number of admissions to a hospital, psychiatric hospital, nursing or convalescent home in the past 12 months (up to 5 or more admissions which is coded as 5)

hospdays

number of nights in a hospital, etc. during most recent admission: taken, where appropriate, as the mid-point of the intervals 1, 2, 3, 4, 5, 6, 7, 8-14, 15-30, 31-60, 61-79 with 80 or more admissions coded as 80. If no admission in past 12 months then equals zero.

medecine

total number of prescribed and nonprescribed medications used in past 2 days

prescrib

total number of prescribed medications used in past 2 days

nonpresc

total number of nonprescribed medications used in past 2 days

Source

Cameron, A.C. and P.K. Trivedi (1986) “Econometric Models Based on Count Data: Comparisons and Applications of Some Estimators and Tests”, Journal of Applied Econometrics, 1, 29-54..

References

Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 3.

See Also

Doctor, DoctorContacts, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Contacts With Medical Doctor

Description

a cross-section from 1977–1978

number of observations : 20186

Usage

data(DoctorContacts)

Format

A time series containing :

mdu

number of outpatient visits to a medical doctor

lc

log(coinsrate+1) where coinsurance rate is 0 to 100

idp

individual deductible plan ?

lpi

log(annual participation incentive payment) or 0 if no payment

fmde

log(max(medical deductible expenditure)) if IDP=1 and MDE>1 or 0 otherwise

physlim

physical limitation ?

ndisease

number of chronic diseases

health

self–rate health (excellent,good,fair,poor)

linc

log of annual family income (in $)

lfam

log of family size

educdec

years of schooling of household head

age

exact age

sex

sex (male,female)

child

age less than 18 ?

black

is household head black ?

Source

Deb, P. and P.K. Trivedi (2002) “The Structure of Demand for Medical Care: Latent Class versus Two-Part Models”, Journal of Health Economics, 21, 601–625.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 553–556 and 565.

See Also

Doctor, MedExp, DoctorAUS, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Earnings for Three Age Groups

Description

a cross-section from 1988-1989

number of observations : 4266

observation : individuals

country : United States

Usage

data(Earnings)

Format

A dataframe containing :

age

age groups, a factor with levels (g1,g2,g3)

y

average annual earnings, in 1982 US dollars

Source

Mills, Jeffery A. and Sourushe Zandvakili (1997) “Statistical Inference via Bootstrapping for Measures of Inequality”, Journal of Applied Econometrics, 12(2), pp. 133-150.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 5 and 7.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Cost Function for Electricity Producers

Description

a cross-section from 1970 to 1970

number of observations : 158

observation : production units

country : United States

Usage

data(Electricity)

Format

A dataframe containing :

cost

total cost

q

total output

pl

wage rate

sl

cost share for labor

pk

capital price index

sk

cost share for capital

pf

fuel price

sf

cost share for fuel

Source

Christensen, L. and W. H. Greene (1976) “Economies of scale in U.S. electric power generation”, Journal of Political Economy, 84, 655-676.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, chapter 4, 317-320.

Hayashi, F. (2000) Econometrics, Princeton University Press, https://archive.org/details/econometrics0000haya, chapter 1, 76-84.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Extramarital Affairs Data

Description

a cross-section

number of observations : 601

observation : individuals

country : United States

Usage

data(Fair)

Format

A dataframe containing :

sex

a factor with levels (male,female)

age

age

ym

number of years married

child

children ? a factor

religious

how religious, from 1 (anti) to 5 (very)

education

education

occupation

occupation, from 1 to 7, according to Hollingshead's classification (reverse numbering)

rate

self rating of marriage, from 1 (very unhappy) to 5 (very happy)

nbaffairs

number of affairs in past year

Source

Fair, R. (1977) “A note on the computation of the tobit estimator”, Econometrica, 45, 1723-1727.

https://fairmodel.econ.yale.edu/rayfair/pdf/1978A200.PDF.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F22.2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Drunk Driving Laws and Traffic Deaths

Description

a panel of 48 observations from 1982 to 1988

number of observations : 336

observation : regional

country : United States

Usage

data(Fatality)

Format

A dataframe containing :

state

state ID code

year

year

mrall

traffic fatality rate (deaths per 10000)

beertax

tax on case of beer

mlda

minimum legal drinking age

jaild

mandatory jail sentence ?

comserd

mandatory community service ?

vmiles

average miles per driver

unrate

unemployment rate

perinc

per capita personal income

Source

Pr. Christopher J. Ruhm, Department of Economics, University of North Carolina.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 8.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Files containing financial crisis data

Description

FinancialCrisisFiles is an object of class financialCrisisFiles created by the financialCrisisFiles function in Ecfun. It describes files containing data on financial crises downloadable from https://web.archive.org/web/20150419090824/http://www.reinhartandrogoff.com/data/browse-by-topic/topics/7.

NOTE: When this dataset was created it was downloaded from http://www.reinhartandrogoff.com/data/browse-by-topic/topics/7. However, it was "Not Found" in testing on 2020-02-09. Fortunately the data are still available on the Internet Archive.

Usage

data(FinancialCrisisFiles)

Details

Reinhart and Rogoff (http://www.reinhartandrogoff.com) provide numerous data sets analyzed in their book, "This Time Is Different: Eight Centuries of Financial Folly". Of interest here are data on financial crises of various types for 70 countries spanning the years 1800 - 2010, downloadable from http://www.reinhartandrogoff.com/data/browse-by-topic/topics/7/.

Version 0.2-3 of the Ecfun package included a function financialCrisisFiles that produced a list of class financialCrisisFiles describing four different Excel files in very similar formats with one sheet per Country and a few extra descriptor sheets. This data object FinancialCrisisFiles was produced by that function. That function required the gdata package, and users of that package were advised to terminate use of it, because it was scheduled to be removed from CRAN along with all packages that used it. Since Reinhart and Rogoff seemed not to be actively maintaining that dataset, there seemed little need to do the work required to make the Ecfun::financialCrisisFiles work without gdata, so it was removed from Ecfun version 2.0-4.

Value

FinancialCrisisFiles is a list with components carrying the names of files to be read. Each component is a list of optional arguments to pass to do.call(read.xls, ...) to read the sheet with name = name of that component. (This read.xls was part of the gdata package, which may no longer be available on CRAN.)

This corresponds to the files downloaded from http://www.reinhartandrogoff.com/data/browse-by-topic/topics/7/ in January 2013 (except for the fourth, which was not available there because of an error with the web site but instead was obtained directly from Prof. Reinhart).

Author(s)

Spencer Graves

Source

http://www.reinhartandrogoff.com

References

Carmen M. Reinhart and Kenneth S. Rogoff (2009) This Time Is Different: Eight Centuries of Financial Folly, Princeton U. Pr.

Choice of Fishing Mode

Description

a cross-section

number of observations : 1182

observation : individuals

country : United States

Usage

data(Fishing)

Format

A dataframe containing :

mode

recreation mode choice, on of : beach, pier, boat and charter

price

price for chosen alternative

catch

catch rate for chosen alternative

pbeach

price for beach mode

ppier

price for pier mode

pboat

price for private boat mode

pcharter

price for charter boat mode

cbeach

catch rate for beach mode

cpier

catch rate for pier mode

cboat

catch rate for private boat mode

ccharter

catch rate for charter boat mode

income

monthly income

Source

Herriges, J. A. and C. L. Kling (1999) “Nonlinear Income Effects in Random Utility Models”, Review of Economics and Statistics, 81, 62-72.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 463–466, 486 and 491–495.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Exchange Rates of US Dollar Against Other Currencies

Description

monthly observations from 1979–01 to 2001–12

number of observations : 276

Usage

data(Forward)

Format

A time series containing :

usdbp

exchange rate USD/British Pound Sterling

usdeuro

exchange rate US D/Euro

eurobp

exchange rate Euro/Pound

usdbp1

1 month forward rate USD/Pound

usdeuro1

1 month forward rate USD/Euro

eurobp1

1 month forward rate Euro/Pound

usdbp3

3 month forward rate USD/Pound

usdeuro3

month forward rate USD/Euro

eurobp3

month forward rate Euro/Pound

Source

Datastream

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 4.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Data from the Television Game Show Friend Or Foe ?

Description

a cross-section from 2002–03

number of observations : 227

observation : individuals

country : United States

Usage

data(FriendFoe)

Format

A dataframe containing :

sex

contestant's sex

white

is contestant white ?

age

contestant's age in years

play

contestant's choice : a factor with levels "foe" and "friend". If both players play "friend", they share the trust box, if both play "foe", both players receive zero prize, if one of them play "foe" and the other one "friend", the "foe" player receive the entire trust box and the "friend" player nothing

round

round in which contestant is eliminated, a factor with levels ("1","2","3")

season

season show, a factor with levels ("1","2")

cash

the amount of cash in the trust box

sex1

partner's sex

white1

is partner white ?

age1

partner's age in years

play1

partner's choice : a factor with levels "foe" and "friend"

win

money won by contestant

win1

money won by partner

Source

Kalist, David E. (2004) “Data from the Television Game Show "Friend or Foe?"”, Journal of Statistics Education, 12(3).

References

Journal of Statistics Education's data archive : https://jse.amstat.org/jse_data_archive.htm.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Daily Observations on Exchange Rates of the US Dollar Against Other Currencies

Description

daily observations from 1980–01 to 1987–05–21

number of observations : 1867

observation : country

country : World

Usage

data(Garch)

Format

A dataframe containing :

date

date of observation (yymmdd)

day

day of the week (a factor)

dm

exchange rate Dollar/Deutsch Mark

ddm

dm-dm(-1)

bp

exchange rate of Dollar/British Pound

cd

exchange rate of Dollar/Canadian Dollar

dy

exchange rate of Dollar/Yen

sf

exchange rate of Dollar/Swiss Franc

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 8.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Gasoline Consumption

Description

a panel of 18 observations from 1960 to 1978

number of observations : 342

observation : country

country : OECD

Usage

data(Gasoline)

Format

A dataframe containing :

country

a factor with 18 levels

year

the year

lgaspcar

logarithm of motor gasoline consumption per auto

lincomep

logarithm of real per-capita income

lrpmg

logarithm of real motor gasoline price

lcarpcap

logarithm of the stock of cars per capita

Source

Baltagi, B.H. and Y.J. Griggin (1983) “Gasoline demand in the OECD: an application of pooling and testing procedures”, European Economic Review, 22.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wage Data

Description

a cross-section from 1980

number of observations : 758

observation : individuals

country : United States

Usage

data(Griliches)

Format

A dataframe containing :

rns

residency in the southern states (first observation) ?

rns80

same variable for 1980

mrt

married (first observation) ?

mrt80

same variable for 1980

smsa

residency in metropolitan areas (first observation) ?

smsa80

same variable for 1980

med

mother's education in years

iq

IQ score

kww

score on the “knowledge of the world of work” test

year

year of the observation

age

age (first observation)

age80

same variable for 1980

school

completed years of schooling (first observation)

school80

same variable for 1980

expr

experience in years (first observation)

expr80

same variable for 1980

tenure

tenure in years (first observation)

tenure80

same variable for 1980

lw

log wage (first observation)

lw80

same variable for 1980

Source

Blackburn, M. and Neumark D. (1992) “Unobserved ability, efficiency wages, and interindustry wage differentials”, Quarterly Journal of Economics, 107, 1421-1436.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 3, 250-256.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Grunfeld Investment Data

Description

a panel of 20 annual observations from 1935 to 1954 on each of 10 firms.

number of observations : 200

observation : production units

country : United States

Usage

data(Grunfeld)

Format

A dataframe containing :

firm

observation

year

date

inv

gross Investment

value

value of the firm

capital

stock of plant and equipment

Details

There are several versions of these data.

GrunfeldGreene is "A data frame containing 20 annual observations on 3 variables for 5 firms." That dataset reportedly contains errors but is maintained in that way to avoid breaking the code of others who use it. That help file also provides a link to the corrected version.

See also for a version with only 5 firms.

Source

Moody's Industrial Manual, Survey of Current Business.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, Table F13.1.

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations, GrunfeldGreene,

Index.Time.Series

Heating and Cooling System Choice in Newly Built Houses in California

Description

a cross-section

number of observations : 250

observation : households

country : California

Usage

data(HC)

Format

A dataframe containing :

depvar

heating system, one of gcc (gas central heat with cooling), ecc (electric central resistance heat with cooling), erc (electric room resistance heat with cooling), hpc (electric heat pump which provides cooling also), gc (gas central heat without cooling, ec (electric central resistance heat without cooling), er (electric room resistance heat without cooling)

ich.z

installation cost of the heating portion of the system

icca

installation cost for cooling

och.z

operating cost for the heating portion of the system

occa

operating cost for cooling

income

annual income of the household

References

Kenneth Train's home page : https://eml.berkeley.edu/~train/.

See Also

Heating, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Cybersecurity breaches reported to the US Department of Health and Human Services

Description

Since October 2009 organizations in the U.S. that store data on human health are required to report any incident that compromises the confidentiality of 500 or more patients / human subjects (45 C.F.R. 164.408) These reports are publicly available. HHSCyberSecurityBreaches was downloaded from the Office for Civil Rights of the U.S. Department of Health and Human Services, 2015-02-26

Usage

data(HHSCyberSecurityBreaches)

Format

A dataframe containing 1151 observations of 9 variables:

Name.of.Covered.Entity

A character vector identifying the organization involved in the breach.

State

A factor giving the two-letter abbreviation of the US state or territory where the breach occurred. This has 52 levels for the 50 states plus the District of Columbia (DC) and Puerto Rico (PR).

Covered.Entity.Type

A factor giving the organization type of the covered entity with levels "Business Associate", "Health Plan", "Healthcare Clearing House", and "Healthcare Provider"

Individuals.Affected

An integer giving the number of humans whose records were compromised in the breach. This is 500 or greater; U.S. law requires reports of breaches involving 500 or more records but not of breaches involving fewer.

Breach.Submission.Date

Date when the breach was reported.

Type.of.Breach

A factor giving one of 29 different combinations of 7 different breach types, separated by ", ": "Hacking/IT Incident", "Improper Disposal", "Loss", "Other", "Theft", "Unauthorized Access/Disclosure", and "Unknown"

Location.of.Breached.Information

A factor giving one of 47 different combinations of 8 different location categories: "Desktop Computer", "Electronic Medical Record", "Email", "Laptop", "Network Server", "Other", "Other Portable Electronic Device", "Paper/Films"

Business.Associate.Present

Logical = (Covered.Entity.Type == "Business Associate")

Web.Description

A character vector giving a narrative description of the incident.

Details

This contains the breach report data downloaded 2015-02-26 from the US Health and Human Services. This catalogs reports starting 2009-10-21. Earlier downloads included a few breaches prior to 2009 when the law was enacted (inconsistently reported), and a date for breach occurrence in addition to the date of the report.

The following corrections were made to the file:

Source

"Breaches Affecting 500 or More Individuals" downloaded from the Office for Civil Rights of the U.S. Department of Health and Human Services, 2015-02-26

See Also

breaches for an earlier download of these data. The exact reporting requirements and even the number and definitions of variables included in the data.frame have changed.

Examples

##
## 1.  mean(Individuals.Affected)
##
mean(HHSCyberSecurityBreaches$Individuals.Affected)
##
## 2.  Basic Breach Types
##
tb <- as.character(HHSCyberSecurityBreaches$Type.of.Breach)
tb. <- strsplit(tb, ', ')
table(unlist(tb.))
# 8 levels, but two are the same apart from 
# a trailing blank.  
##
## 3.  Location.of.Breached.Information 
##
lb <- as.character(HHSCyberSecurityBreaches[[
          'Location.of.Breached.Information']])
table(lb)
lb. <- strsplit(lb, ', ')
table(unlist(lb.))
# 8 levels 
table(sapply(lb., length))
#   1    2    3    4    5    6    7    8 
#1007  119   13    8    1    1    1    1 
# all 8 levels together observed once 
# There are 256 = 2^8 possible combinations 
# of which 47 actually occur in these data.

Health Insurance and Hours Worked By Wives

Description

a cross-section from 1993

number of observations : 22272

observation : individuals

country : United States

Usage

data(HI)

Format

A dataframe containing :

whrswk

hours worked per week by wife

hhi

wife covered by husband's HI ?

whi

wife has HI thru her job ?

hhi2

husband has HI thru own job ?

education

a factor with levels, "<9years", "9-11years", "12years", "13-15years", "16years", ">16years"

race

one of white, black, other

hispanic

Hispanic ?

experience

years of potential work experience

kidslt6

number of kids under age of 6

kids618

number of kids 6–18 years old

husby

husband's income in thousands of dollars

region

one of other, northcentral, south, west

wght

sampling weight

Source

Olson, Craig A. (1998) “A comparison of parametric and semiparametric estimates of the effect of spousal health insurance coverage on weekly hours worked by wives”, Journal of Applied Econometrics, 13(5), September–October, 543–565.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Heating System Choice in California Houses

Description

a cross-section

number of observations : 900

observation : households

country : California

Usage

data(Heating)

Format

A dataframe containing :

idcase

id

depvar

heating system, one of gc (gas central), gr (gas room), ec (electric central), er (electric room), hp (heat pump)

ic.z

installation cost for heating system z (defined for the 5 heating systems)

oc.z

annual operating cost for heating system z (defined for the 5 heating systems)

pb.z

ratio oc.z/ic.z

income

annual income of the household

agehed

age of the household head

rooms

numbers of rooms in the house

References

Kenneth Train's home page : https://eml.berkeley.edu/~train/.

See Also

HC, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Hedonic Prices of Census Tracts in Boston

Description

a cross-section

number of observations : 506

observation : regional

country : United States

Usage

data(Hedonic)

Format

A dataframe containing :

mv

median value of owner–occupied homes

crim

crime rate

zn

proportion of 25,000 square feet residential lots

indus

proportion of nonretail business acres

chas

is the tract bounds the Charles River ?

nox

annual average nitrogen oxide concentration in parts per hundred million

rm

average number of rooms

age

proportion of owner units built prior to 1940

dis

weighted distances to five employment centers in the Boston area

rad

index of accessibility to radial highways

tax

full value property tax rate ($ / $10,000)

ptratio

pupil/teacher ratio

blacks

proportion of blacks in the population

lstat

proportion of population that is lower status

townid

town identifier

Source

Harrison, D. and D.L. Rubinfeld (1978) “Hedonic housing prices and the demand for clean air”, Journal of Environmental Economics Ans Management, 5, 81–102.

Belsley, D.A., E. Kuh and R. E. Welsch (1980) Regression diagnostics: identifying influential data and sources of collinearity, John Wiley, New–York.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

The Boston HMDA Data Set

Description

a cross-section from 1997-1998

number of observations : 2381 observation : individuals country : United States

In package version 0.2-9 and earlier this dataset was called Hdma.

Usage

data(Hmda)

Format

A dataframe containing :

dir

debt payments to total income ratio

hir

housing expenses to income ratio

lvr

ratio of size of loan to assessed value of property

ccs

consumer credit score from 1 to 6 (a low value being a good score)

mcs

mortgage credit score from 1 to 4 (a low value being a good score)

pbcr

public bad credit record ?

dmi

denied mortgage insurance ?

self

self employed ?

single

is the applicant single ?

uria

1989 Massachusetts unemployment rate in the applicant's industry

condominium

is unit a condominium ? (was called comdominiom in version 0.2-9 and earlier versions of the package)

black

is the applicant black ?

deny

mortgage application denied ?

Source

Federal Reserve Bank of Boston.

Munnell, Alicia H., Geoffrey M.B. Tootell, Lynne E. Browne and James McEneaney (1996) “Mortgage lending in Boston: Interpreting HMDA data”, American Economic Review, 25-53.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 9.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Sales Prices of Houses in the City of Windsor

Description

a cross-section from 1987

number of observations : 546

observation : goods

country : Canada

Usage

data(Housing)

Format

A dataframe containing :

price

sale price of a house

lotsize

the lot size of a property in square feet

bedrooms

number of bedrooms

bathrms

number of full bathrooms

stories

number of stories excluding basement

driveway

does the house has a driveway ?

recroom

does the house has a recreational room ?

fullbase

does the house has a full finished basement ?

gashw

does the house uses gas for hot water heating ?

airco

does the house has central air conditioning ?

garagepl

number of garage places

prefarea

is the house located in the preferred neighbourhood of the city ?

Source

Anglin, P.M. and R. Gencay (1996) “Semiparametric estimation of a hedonic price function”, Journal of Applied Econometrics, 11(6), 633-648.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 3.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Housing Starts

Description

quarterly observations from 1960-1 to 2001-4

number of observations : 168

observation : country

country : Canada

Usage

data(Hstarts)

Format

A time series containing :

hs

the log of urban housing starts in Canada, not seasonally adjusted, CANSIM series J6001, converted to quarterly

hssa

the log of urban housing starts in Canada, seasonally adjusted, CANSIM series J9001, converted to quarterly. Observations prior to 1966:1 are missing

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 13.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Ice Cream Consumption

Description

four–weekly observations from 1951–03–18 to 1953–07–11

number of observations : 30

observation : country

country : United States

Usage

data(Icecream)

Format

A time series containing :

cons

consumption of ice cream per head (in pints);

income

average family income per week (in US Dollars);

price

price of ice cream (per pint);

temp

average temperature (in Fahrenheit);

Source

Hildreth, C. and J. Lu (1960) Demand relations with autocorrelated disturbances, Technical Bulletin No 2765, Michigan State University.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 4.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Seasonally Unadjusted Quarterly Data on Disposable Income and Expenditure

Description

quarterly observations from 1971–1 to 1985–2

number of observations : 58

observation : country

country : United Kingdom

Usage

data(IncomeUK)

Format

A time series containing :

income

total disposable income (million Pounds, current prices)

consumption

consumer expenditure (million Pounds, current prices)

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapters 8 and 9.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Econometric fields

Description

Economic fields

Description

Observations

Description

Source

Description

Time Series

Description

Monthly Interest Rates

Description

monthly observations from 1946–12 to 1991–02

number of observations : 531

observation : country

country : United–States

Usage

data(Irates)

Format

A time series containing :

r1

interest rate for a maturity of 1 months (% per year).

r2

interest rate for a maturity of 2 months (% per year).

r3

interest rate for a maturity of 3 months (% per year).

r5

interest rate for a maturity of 5 months (% per year).

r6

interest rate for a maturity of 6 months (% per year).

r11

interest rate for a maturity of 11 months (% per year).

r12

interest rate for a maturity of 12 months (% per year).

r36

interest rate for a maturity of 36 months (% per year).

r60

interest rate for a maturity of 60 months (% per year).

r120

interest rate for a maturity of 120 months (% per year).

Source

McCulloch, J.H. and H.C. Kwon (1993) U.S. term structure data, 1947–1991, Ohio State Working Paper 93-6, Ohio State University, Columbus.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 8.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Economic Journals Data Set

Description

a cross-section from 2000

number of observations : 180

observation : goods

Usage

data(Journals)

Format

A dataframe containing :

title

journal title

pub

publisher

society

scholarly society ?

libprice

library subscription price

pages

number of pages

charpp

characters per page

citestot

total number of citations

date1

year journal was founded

oclc

number of library subscriptions

field

field description

Source

Professor Theodore Bergstrom of the Department of Economics at the University of California, San Diego.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 6.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Willingness to Pay for the Preservation of the Kakadu National Park

Description

a cross-section

number of observations : 1827

observation : individuals

country : Australia

Usage

data(Kakadu)

Format

A dataframe containing :

lower

lower bound of willingness to pay, 0 if observation is left censored

upper

upper bound of willingness to pay, 999 if observation is right censored

answer

an ordered factor with levels nn (respondent answers no, no), ny (respondent answers no, yes or yes, no), yy (respondent answers yes, yes)

recparks

the greatest value of national parks and nature reserves is in recreation activities (from 1 to 5)

jobs

jobs are the most important thing in deciding how to use our natural resources (from 1 to 5)

lowrisk

development should be allowed to proceed where environmental damage from activities such as mining is possible but very unlikely (from 1 to 5)

wildlife

it's important to have places where wildlife is preserved (from 1 to 5)

future

it's important to consider future generations (from 1 to 5)

aboriginal

in deciding how to use areas such as Kakadu national park, their importance to the local aboriginal people should be a major factor (from 1 to 5)

finben

in deciding how to use our natural resources such as mineral deposits and forests, the most important thing is the financial benefits for Australia (from 1 to 5)

mineparks

if areas within natural parks are set aside for development projects such as mining, the value of the parks is greatly reduced (from 1 to 5)

moreparks

there should be more national parks created from state forests (from 1 to 5)

gov

the government pays little attention to the people in making decisions (from 1 to 4)

envcon

the respondent recycles things such as paper or glass and regularly buys unbleached toilet paper or environmentally friendly products?

vparks

the respondent has visited a national park or bushland recreation area in the previous 12 months?

tvenv

the respondent watches TV programs about the environment? (from 1 to 9)

conservation

the respondent is member of a conservation organization?

sex

male,female

age

age

schooling

years of schooling

income

respondent's income in thousands of dollars

major

the respondent received the major–impact scenario of the Kakadu conservation zone survey ?

Source

Werner, Megan (1999) “Allowing for zeros in dichotomous–choice contingent–valuation models”, Journal of Business and Economic Statistics, 17(4), October, 479–486.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Choice of Brand for Ketchup

Description

a cross-section

number of observations : 4956

observation : individuals

country : United States

Usage

data(Ketchup)

Format

A dataframe containing :

hid

individuals identifiers

id

purchase identifiers

choice

one of heinz, hunts, delmonte, stb (store brand)

price.z

price of brand z

Source

Kim, Byong–Do, Robert C. Blattberg and Peter E. Rossi (1995) “Modeling the distribution of price sensitivity and implications for optimal retail pricing”, Journal of Business Economics and Statistics, 13(3), 291.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Catsup, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Klein's Model I

Description

annual observations from 1920 to 1941

number of observations : 22

observation : country

country : United States

Usage

data(Klein)

Format

A time series containing :

cons

consumption

profit

corporate profits

privwage

private wage bill

inv

investment

lcap

previous year's capital stock

gnp

GNP

pubwage

government wage bill

govspend

government spending

taxe

taxes

Source

Klein, L. (1950) Economic fluctuations in the United States, 1921-1941, New York, John Wiley and Sons.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F15.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Dollar Sterling Exchange Rate

Description

annual observations from 1791 to 1990

number of observations : 200

observation : country

country : United Kingdom

Usage

data(LT)

Format

A time series containing :

s

US *Dollar / *Pound exchange rate

uswpi

US wholesale price index, normalized to 100 for 1914

ukwpi

US wholesale price index, normalized to 100 for 1914

Source

Lothian, J. and M. Taylor (1996) “Real exchange rate behavior: the recent float from the perspective of the past two centuries”, Journal of Political Economy, 104, 488-509.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 9, 613-621.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wages and Hours Worked

Description

a panel of 532 observations from 1979 to 1988

number of observations : 5320

Usage

data(LaborSupply)

Format

A dataframe containing :

lnhr

log of annual hours worked

lnwg

log of hourly wage

kids

number of children

age

age

disab

bad health

id

id

year

year

Source

Ziliak, Jim (1997) “Efficient Estimation With Panel Data when Instruments are Predetermined: An Empirical Comparison of Moment-Condition Estimators”, Journal of Business and Economic Statistics, 419–431.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 708–15, 754–6.

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Belgian Firms

Description

a cross-section from 1996

number of observations : 569

observation : production units

country : Belgium

Usage

data(Labour)

Format

A dataframe containing :

capital

total fixed assets, end of 1995 (in 1000000 euro)

labour

number of workers (employment)

output

value added (in 1000000 euro)

wage

wage costs per worker (in 1000 euro)

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 4.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

The Longley Data

Description

annual observations from 1947 to 1962

number of observations : 16

observation : country

country : United States

Usage

data(Longley)

Format

A time series containing :

employ

employment (1,000s)

price

GNP deflator

gnp

nominal GNP (millions)

armed

armed forces

Source

Longley, J. (1967) “An appraisal of least squares programs from the point of view of the user”, Journal of the American Statistical Association, 62, 819-841.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F4.2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

The Massachusetts Test Score Data Set

Description

a cross-section from 1997-1998

number of observations : 220

observation : schools

country : United States

Usage

data(MCAS)

Format

A dataframe containing :

code

district code (numerical)

municipa

municipality (name)

district

district name

regday

spending per pupil, regular

specneed

spending per pupil, special needs

bilingua

spending per pupil, bilingual

occupday

spending per pupil, occupational

totday

spending per pupil, total

spc

students per computer

speced

special education students

lnchpct

eligible for free or reduced price lunch

tchratio

students per teacher

percap

per capita income

totsc4

4th grade score (math+english+science)

totsc8

8th grade score (math+english+science)

avgsalary

average teacher salary

pctel

percent English learners

Source

Massachusetts Comprehensive Assessment System (MCAS), Massachusetts Department of Education, 1990 U.S. Census.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 7.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Growth of Disposable Income and Treasury Bill Rate

Description

quarterly observations from 1963-3 to 1975-4

number of observations : 50

observation : country

country : United States

Usage

data(MW)

Format

A time series containing :

rdi

the rate of growth of real U.S. disposable income, seasonally adjusted

trate

the U.S. treasury bill rate

Source

MacKinnon, J. G. and H. T. White (1985) “Some heteroskedasticity consistent covariance matrix estimators with improved finite sample properties”, Journal of Econometrics, 29, 305-325.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 5.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Macroeconomic Time Series for the United States

Description

quarterly observations from 1959-1 to 2000-4

number of observations : 168

observation : country

country : United States

Usage

data(Macrodat)

Format

A time series containing :

lhur

unemployment rate (average of months in quarter)

punew

CPI (Average of Months in Quarter)

fyff

federal funds interest rate (last month in quarter)

fygm3

3 month treasury bill interest rate (last month in quarter)

fygt1

1 year treasury bond interest rate (last month in quarter)

exruk

dollar / Pound exchange rate (last month in quarter)

gdpjp

real GDP for Japan

Source

Bureau of Labor Statistics, OECD, Federal Reserve.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 12 and 14.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wages and Education of Young Males

Description

a panel of 545 observations from 1980 to 1987

number of observations : 4360

observation : individuals

country : United States

Usage

data(Males)

Format

A dataframe containing :

nr

identifier

year

year

school

years of schooling

exper

years of experience (=age-6-school)

union

wage set by collective bargaining ?

ethn

a factor with levels (black, hisp, other)

maried

married ?

health

health problem ?

wage

log of hourly wage

industry

a factor with 12 levels

occupation

a factor with 9 levels

residence

a factor with levels (rural area, north east, northern central, south)

Source

National Longitudinal Survey (NLS Youth Sample).

Vella, F. and M. Verbeek (1998) “Whose wages do unions raise ? A dynamic model of unionism and wage”, Journal of Applied Econometrics, 13, 163–183.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 10.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Manufacturing Costs

Description

annual observations from 1947 to 1971

number of observations : 25

observation : country

country : United States

Usage

data(ManufCost)

Format

A time series containing :

cost

cost index

sk

capital cost share

sl

labor cost share

se

energy cost share

sm

materials cost share

pk

capital price

pl

labor price

pe

energy price

pm

materials price

Source

Berndt, E. and D. Wood (1975) “Technology, prices and the derived demand for energy”, Journal of Economics and Statistics, 57, 376-384.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F14.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Level of Calculus Attained for Students Taking Advanced Micro–economics

Description

a cross-section from 1983 to 1986

number of observations : 609

observation : individuals

country : United States

Usage

data(Mathlevel)

Format

A dataframe containing :

mathlevel

highest level of math attained , an ordered factor with levels 170, 171a, 172, 171b, 172b, 221a, 221b

sat

sat Math score

language

foreign language proficiency ?

sex

male, female

major

one of other, eco, oss (other social sciences), ns (natural sciences), hum (humanities)

mathcourse

number of courses in advanced math (0 to 3)

physiccourse

number of courses in physics (0 to 2)

chemistcourse

number of courses in chemistry (0 to 2)

Source

Butler, J.S., T. Aldrich Finegan and John J. Siegfried (1998) “Does more calculus improve student learning in intermediate micro and macroeconomic theory ?”, Journal of Applied Econometrics, 13(2), April, 185–202.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Structure of Demand for Medical Care

Description

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/

number of observations : 5574

Usage

data(MedExp)

Format

A time series containing :

med

annual medical expenditures in constant dollars excluding dental and outpatient mental

lc

log(coinsrate+1) where coinsurance rate is 0 to 100

idp

individual deductible plan ?

lpi

log(annual participation incentive payment) or 0 if no payment

fmde

log(max(medical deductible expenditure)) if IDP=1 and MDE>1 or 0 otherwise

physlim

physical limitation ?

ndisease

number of chronic diseases

health

self–rate health (excellent,good,fair,poor)

linc

log of annual family income (in $)

lfam

log of family size

educdec

years of schooling of household head

age

exact age

sex

sex (male,female)

child

age less than 18 ?

black

is household head black ?

Source

Deb, P. and P.K. Trivedi (2002) “The Structure of Demand for Medical Care: Latent Class versus Two-Part Models”, Journal of Health Economics, 21, 601–625.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge.

See Also

DoctorContacts, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Production for SIC 33

Description

a cross-section

number of observations : 27

observation : regional

country : United States

Usage

data(Metal)

Format

A dataframe containing :

va

output

labor

labor input

capital

capital input

Source

Aigner, D., K. Lovell and P. Schmidt (1977) “Formulation and estimation of stochastic frontier production models”, Journal of Econometrics, 6, 21-37.

Hildebrand, G. and T. Liu (1957) Manufacturing production functions in the United States, Ithaca, N.Y.: Cornell University Press.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F6.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Inflation and Interest Rates

Description

monthly observations from 1950-2 to 1990-12

number of observations : 491

observation : country

country : United States

Usage

data(Mishkin)

Format

A time series containing :

pai1

one-month inflation rate (in percent, annual rate)

pai3

three-month inflation rate (in percent, annual rate)

tb1

one-month T-bill rate (in percent, annual rate)

tb3

three-month T-bill rate (in percent, annual rate)

cpi

CPI for urban consumers, all items (the 1982-1984 average is set to 100)

Source

Mishkin, F. (1992) “Is the Fisher effect for real ?”, Journal of Monetary Economics, 30, 195-215.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 2, 176-184.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Mode Choice

Description

a cross-section

number of observations : 453

observation : individuals

Usage

data(Mode)

Format

A dataframe containing :

choice

one of car, carpool, bus or rail

cost.z

cost of mode z

time.z

time of mode z

References

Kenneth Train's home page : https://eml.berkeley.edu/~train/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Data to Study Travel Mode Choice

Description

a cross-section

number of observations : 840

observation : individuals

country : Australia

Usage

data(ModeChoice)

Format

A dataframe containing :

mode

choice : air, train, bus or car

ttme

terminal waiting cost time, 0 for car

invc

in vehicle cost-cost component

invt

travel time in vehicle

gc

generalized cost measure

hinc

household income

psize

party size in mode chosen

Source

Greene, W.H. and D. Hensher (1997) Multinomial logit and discrete choice models in Greene, W. H. (1997) LIMDEP version 7.0 user's manual revised, Plainview, New York econometric software, Inc .

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F21.2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

International Expansion of U.S. MOFAs (majority–owned Foreign Affiliates in Fire (finance, Insurance and Real Estate)

Description

a cross-section from 1982

number of observations : 50

observation : country

country : United States

Usage

data(Mofa)

Format

A dataframe containing :

capexp

capital expenditures made by the MOFAs of nonbank U.S. corporations in finance, insurance and real estate. Source: "U.S. Direct Investment Abroad: 1982 Benchmark Survey data." Table III.C 6.

gdp

gross domestic product. Source: "World Bank, World Development Report 1984." Table 3. (This variable is scaled by a factor of 1/100,000)

sales

sales made by the majority owned foreign affiliates of nonbank U.S. parents in finance, insurance and real estate. Source: "U.S. Direct Investment Abroad: 1982 Benchmark Survey Data." Table III.D 3. (This variable is scaled by a factor of 1/100)

nbaf

the number of U.S. affiliates in the host country. Source: "U.S. Direct Investment Abroad: 1982 Benchmark Survey Data." Table 5. (This variable is scaled by a factor of 1/100)

netinc

net income earned by MOFAs of nonbank U.S. corporations operating in the nonbanking financial sector of the host country. Source: "U.S. Direct Investment Abroad: 1982 Benchmark Survey Data." Table III.D 6.(This variable is scaled by a factor of 1/10)

Source

Ioannatos, Petros E. (1995) “Censored regression estimation under unobserved heterogeneity : a stochastic parameter approach”, Journal of Business and Economics Statistics, 13(3), July, 327–335.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Money, GDP and Interest Rate in Canada

Description

quarterly observations from 1967-1 to 1998-4

number of observations : 128

observation : country

country : Canada

Usage

data(Money)

Format

A time series containing :

m

log of the real money supply

y

the log of GDP, in 1992 dollars, seasonally adjusted

p

the log of the price level

r

the 3-month treasury till rate

Source

CANSIM Database of Statistics Canada.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 7 and 8.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Macroeconomic Series for the United States

Description

quarterly observations from 1954–01 to 1994–12

number of observations : 164

country : United States

Usage

data(MoneyUS)

Format

A time series containing :

m

log of real M1 money stock

infl

quarterly inflation rate (change in log prices), % per year

cpr

commercial paper rate, % per year

y

log real GDP (in billions of 1987 dollars)

tbr

treasury bill rate

Source

Hoffman, D.L. and R.H. Rasche (1996) “Assessing forecast performance in a cointegrated system”, Journal of Applied Econometrics, 11, 495–517.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 9.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Money, National Product and Interest Rate

Description

annual observations from 1900 to 1989

number of observations : 90

observation : country

country : United States

Usage

data(Mpyr)

Format

A time series containing :

m

natural log of M1

p

natural log of the net national product price deflator

y

natural log of the net national product

r

the commercial paper rate in percent at an annual rate

Source

Stock, J. and M. Watson (1999) “Testing for common trends”, Journal of the American Statistical Association, 83, 1097-1107.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 10, 665-667.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Labor Supply Data

Description

a cross-section

number of observations : 753

observation : individuals

country : United States

Usage

data(Mroz)

Format

A dataframe containing :

work

work at home in 1975? (Same carData::Mroz[['lfp']] = labor force participation.)

hoursw

wife's hours of work in 1975

child6

number of children less than 6 years old in household (Same as carData::Mroz['k5'].)

child618

number of children between ages 6 and 18 in household (Same as carData::Mroz['k618'])

agew

wife's age

educw

wife's educational attainment, in years

hearnw

wife's average hourly earnings, in 1975 dollars

wagew

wife's wage reported at the time of the 1976 interview (not= 1975 estimated wage)

hoursh

husband's hours worked in 1975

ageh

husband's age

educh

husband's educational attainment, in years

wageh

husband's wage, in 1975 dollars

income

family income, in 1975 dollars

educwm

wife's mother's educational attainment, in years

educwf

wife's father's educational attainment, in years

unemprate

unemployment rate in county of residence, in percentage points

city

lives in large city (SMSA) ?

experience

actual years of wife's previous labor market experience

Details

These data seem to have come from the same source as carData::Mroz, though each data set has variables not in the other. The variables that are shared have different names.

On 2019-11-04 Bruno Rodrigues explained that Ecdat::Mroz['work'] had the two labels incorrectly swapped, and wooldridge::mroz['inlf'] was correct; wooldridge matches carData::Mroz['lfp'].

Source

Mroz, T. (1987) “The sensitivity of an empirical model of married women's hours of work to economic and statistical assumptions”, Econometrica, 55, 765-799.

1976 Panel Study of Income Dynamics.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F4.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Mroz mroz

Examples

head(Mroz)

#If 'car' and / or 'carData' is also in the path, 
# then use the following to be clear that 
# you want this version: 
head(Ecdat::Mroz)

Municipal Expenditure Data

Description

a panel of 265 observations from 1979 to 1987

number of observations : 2385

observation : regional

country : Sweden

Usage

data(MunExp)

Format

A dataframe containing :

id

identification

year

date

expend

expenditure

revenue

revenue from taxes and fees

grants

grants from Central Government

Source

Dahlberg, M. and E. Johansson (2000) “An examination of the dynamic behavior of local government using GMM boot-strapping methods”, Journal of Applied Econometrics, 21, 333-355.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F18.1.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Willingness to Pay for the Preservation of the Alentejo Natural Park

Description

a cross-section from 1987

number of observations : 312

observation : individuals

country : Portugal

Usage

data(NaturalPark)

Format

A dataframe containing :

bid1

initial bid, in euro

bidh

higher bid

bidl

lower bid

answers

a factor with levels (nn, ny, yn, yy)

age

age in 6 classes

sex

a factor with levels (male,female)

income

income in 8 classes

Source

Nunes, Paulo (2000) Contingent Valuation of the Benefits of natural areas and its warmglow component, PhD thesis 133, FETEW, KU Leuven.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 7.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Cost Function for Electricity Producers, 1955

Description

a cross-section from 1955 to 1955

number of observations : 159

observation : production units

country : United States

Usage

data(Nerlove)

Format

A dataframe containing :

cost

total cost

output

total output

pl

wage rate

sl

cost share for labor

pk

capital price index

sk

cost share for capital

pf

fuel price

sf

cost share for fuel

Source

Nerlove, M. (1963) Returns to scale in electricity industry in Christ, C. ed. (1963) Measurement in Economics: Studies in Mathematical Economics and Econometrics in Memory of Yehuda Grunfeld , Stanford, California, Stanford University Press .

Christensen, L. and W. H. Greene (1976) “Economies of scale in U.S. electric power generation”, Journal of Political Economy, 84, 655-676.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometricanaly0000gree_f4x3, Table F14.2.

Hayashi, F. (2000) Econometrics, Princeton University Press, https://archive.org/details/econometrics0000haya, chapter 1, 76-84.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Evolution of occupational distribution in the US

Description

Proportion of the US population in each of the 283 OCC1950 occupation codes for each year in the Integrated Public Use Microdata Series (IPUMS) - US database.

Usage

data("OCC1950")

Format

A matrix with one row for each of 281 OCC1950 occupation codes in IPUMS-US and one column for each year in their dataset as of 2020-03-17, being c(1850:1880, 1900:2000, 2001:2016).

Details

This dataset was created using the code in the IPUMS vignette in the Ecfun package using tapply(HHWT, IPUMSdata[c("OCC1950", "YEAR")], sum), then normalizing so the total for each year was 1.

In fact a plot of the sums for each year of HHWT were close to the USGDPpresidents$population.K*1000 except for 1970, when they were double.

Universe Note from the IPUMS documentation for their variable OCC1950: "New Workers" are persons seeking employment for the first time, who had not yet secured their first job.

OCC1950 applies the 1950 Census Bureau occupational classification system to occupational data, to enhance comparability across years. For pre-1940 samples created at the University of Minnesota, the alphabetic responses supplied by enumerators were directly coded into the 1950 classification. For other samples, the information in the variable OCC was recoded into the 1950 classification. Codes above 970 are non-occupational responses retained in the historical census samples or blank/unknown. The design of OCC1950 is described at length in "Integrated Occupation and Industry Codes and Occupational Standing Variables in the IPUMS.". The composition of the 1950 occupation categories is described in detail in U.S. Bureau of the Census, Alphabetic Index of Occupations and Industries: 1950 (Washington D.C., 1950).

In 1850-1880, any laborer with no specified industry in a household with a farmer is recoded into farm labor. In 1860-1900, any woman with an occupational response of "housekeeper" enters the non-occupational category "keeping house" if she is related to the head of household. Cases affected by these imputation procedures are identified by an appropriate data quality flag (present in the raw IPUMS data but ignored for this summary).

A parallel variable called OCC1990, available for the samples from 1950 onward, codes occupations into a simplified version of the 1990 occupational coding scheme." [OCC1990 was ignored for the present purposes, because it is not coded for data prior to 1950.]

NOTE: In the 2020-03-17 extraction, there were 283 OCC1950 codes documented, but only 291 of them were actually in the data I got. The codes for "Not yet classified" and "New Workers" were not used.

Source

Steven Ruggles, Sarah Flood, Ronald Goeken, Josiah Grover, Erin Meyer, Jose Pacas, and Matthew Sobek (2020) doi:10.18128/D010.V10.0 IPUMS USA: Version 10.0 [dataset]. Minneapolis, MN: IPUMS.

Examples

data(OCC1950)

Visits to Physician Office

Description

a cross-section

number of observations : 4406

observation : individuals

country : United States

Usage

data(OFP)

Format

A dataframe containing :

ofp

number of physician office visits

ofnp

number of nonphysician office visits

opp

number of physician outpatient visits

opnp

number of nonphysician outpatient visits

emr

number of emergency room visits

hosp

number of hospitalizations

numchron

number of chronic conditions

adldiff

the person has a condition that limits activities of daily living ?

age

age in years (divided by 10)

black

is the person African–American ?

sex

is the person male ?

maried

is the person married ?

school

number of years of education

faminc

family income in 10000$

employed

is the person employed ?

privins

is the person covered by private health insurance?

medicaid

is the person covered by medicaid ?

region

the region (noreast, midwest, west)

hlth

self-perceived health (excellent, poor, other)

Source

Deb, P. and P.K. Trivedi (1997) “Demand for Medical Care by the Elderly: A Finite Mixture Approach”, Journal of Applied Econometrics, 12, 313-326..

References

Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 6.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Oil Investment

Description

a cross-section from 1969 to 1992

number of observations : 53

observation : production units

country : United Kingdom

Usage

data(Oil)

Format

A dataframe containing :

dur

duration of the appraisal lag in months (time span between discovery of an oil field and beginning of development, i.e. approval of annex B).

size

size of recoverable reserves in millions of barrels

waterd

depth of the sea in metres

gasres

size of recoverable gas reserves in billions of cubic feet

operator

equity market value (in 1991 million pounds) of the company operating the oil field

p

real after–tax oil price measured at time of annex B approval

vardp

volatility of the real oil price process measured as the squared recursive standard errors of the regression of pt-pt-1 on a constant

p97

adaptive expectations (with parameter theta=0.97) for the real after–tax oil prices formed at the time of annex B approval

varp97

volatility of the adaptive expectations (with parameter theta=0.97) for real after tax oil prices measured as the squared recursive standard errors of the regression of pt on pte(theta)

p98

adaptive expectations (with parameter theta=0.98) for the real after–tax oil prices formed at the time of annex B approval

varp98

volatility of the adaptive expectations (with parameter theta=0.98) for real after tax oil prices measured as the squared recursive standard errors of the regression of pt on pte(theta)

Source

Favero, Carlo A., M. Hashem Pesaran and Sunil Sharma (1994) “A duration model of irreversible oil investment : theory and empirical evidence”, Journal of Applied Econometrics, 9(S), S95–S112.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

The Orange Juice Data Set

Description

monthly observations from 1948-01 to 2001-06

number of observations : 642

observation : country

country : United States

Usage

data(Orange)

Format

A time series containing :

priceoj

producer price for frozen orange juice

pricefg

producer price index for finished goods

fdd

freezing degree days (from daily minimum temperature recorded at Orlando area airports)

Source

U.S. Bureau of Labor Statistics for PPIOJ and PWFSA, National Oceanic and Atmospheric Administration (NOAA) of the U.S Department of Commerce for fdd.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Price and Earnings Index

Description

annual observations from 1800 to 1931

number of observations : 132

observation : country

country : United States

Usage

data(PE)

Format

A time series containing :

price

S&P composite stock price index

earnings

S&P composite earnings index

Source

Robert Shiller.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 8.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Exchange Rates and Price Indices for France and Italy

Description

monthly observations from 1981–01 to 1996–06

number of observations : 186

observation : country

country : France and Italy

Usage

data(PPP)

Format

A time series containing :

lnit

log price index Italy

lnfr

log price index France

lnx

log exchange rate France/Italy

cpiit

consumer price index Italy

cpifr

consumer price index France

Source

Datastream.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapters 8 and 9.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Panel Survey of Income Dynamics

Description

a cross-section from 1993

number of observations : 4856

observation : individuals

country : United States

Usage

data(PSID)

Format

A dataframe containing :

intnum

1968 interview number

persnum

person number

age

age of individual

educatn

highest grade completed

earnings

total labor income

hours

annual work hours

kids

live births to this individual

married

last known marital status (married, never married, windowed, divorced, separated, NA/DF, no histories)

Source

Panel Survey of Income Dynamics.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 295–300.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Labor Force Participation

Description

a cross-section

number of observations : 872

observation : individuals

country : Switzerland

Usage

data(Participation)

Format

A dataframe containing :

lfp

labour force participation ?

lnnlinc

the log of nonlabour income

age

age in years divided by 10

educ

years of formal education

nyc

the number of young children (younger than 7)

noc

number of older children

foreign

foreigner ?

Source

Gerfin, Michael (1996) “Parametric and semiparametric estimation of the binary response”, Journal of Applied Econometrics, 11(3), 321-340.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 11.

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Dynamic Relation Between Patents and R&D

Description

a panel of 346 observations from 1975 to 1979

number of observations : 1730

observation : production units

country : United States

Usage

data(PatentsHGH)

Format

A dataframe containing :

obsno

firm index

year

year

cusip

Compustat's identifying number for the firm (Committee on Uniform Security Identification Procedures number)

ardsic

a two-digit code for the applied R&D industrial classification (roughly that in Bound, Cummins, Griliches, Hall, and Jaffe, in the Griliches R&D, Patents, and Productivity volume)

scisect

is the firm in the scientific sector ?

logk

the logarithm of the book value of capital in 1972.

sumpat

the sum of patents applied for between 1972-1979.

logr

the logarithm of R&D spending during the year (in 1972 dollars)

logr1

the logarithm of R&D spending (one year lag)

logr2

the logarithm of R&D spending (two years lag)

logr3

the logarithm of R&D spending (three years lag)

logr4

the logarithm of R&D spending (four years lag)

logr5

the logarithm of R&D spending (five years lag)

pat

the number of patents applied for during the year that were eventually granted

pat1

the number of patents (one year lag)

pat2

the number of patents (two years lag)

pat3

the number of patents (three years lag)

pat4

the number of patents (four years lag)

Source

Hall, Bronwyn, Zvi Griliches and Jerry Hausman (1986) “Patents and R&D: Is There a Lag?”, International Economic Review, 27, 265-283.

References

Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 9.

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 792–5.

See Also

PatentsRD, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Patents, R&D and Technological Spillovers for a Panel of Firms

Description

a panel of 181 observations from 1983 to 1991

number of observations : 1629

observation : production units

country : world

Usage

data(PatentsRD)

Format

A dataframe containing :

year

year

fi

firm's id

sector

firm's main industry sector, one of aero (aerospace), chem (chemistry), comput (computer), drugs, elec (electricity), food, fuel (fuel and mining), glass, instr (instruments), machin (machinery), metals, other, paper, soft (software), motor (motor vehicles)

geo

geographic area, one of eu (European Union), japan, usa, rotw (rest of the world)

patent

numbers of European patent applications

rdexp

log of R&D expenditures

spil

log of spillovers

Source

Cincer, Michele (1997) “Patents, R & D and technological spillovers at the firm level : some evidence from econometric count models for panel data”, Journal of Applied Econometrics, 12(3), May–June, 265–280.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/. Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 7.

See Also

PatentsHGH, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Pound-dollar Exchange Rate

Description

weekly observations from 1975 to 1989

number of observations : 778

observation : country

country : Germany

Usage

data(Pound)

Format

A dataframe containing :

date

the date of the observation (19850104 is January, 4, 1985)

s

the ask price of the dollar in units of Pound in the spot market on Friday of the current week

f

the ask price of the dollar in units of Pound in the 30-day forward market on Friday of the current week

s30

the bid price of the dollar in units of Pound in the spot market on the delivery date on a current forward contract

Source

Bekaert, G. and R. Hodrick (1993) “On biases in the measurement of foreign exchange risk premiums”, Journal of International Money and Finance, 12, 115-138.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 6, 438-443.

See Also

DM, Yen, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Returns of Size-based Portfolios

Description

monthly observations from 1959–02 to 1993–11

number of observations : 418

Usage

data(Pricing)

Format

A time series containing :

r1

monthly return on portfolio 1 (small firms)

r2

monthly return on portfolio 2

r3

monthly return on portfolio 3

r4

monthly return on portfolio 4

r5

monthly return on portfolio 5

r6

monthly return on portfolio 6

r7

monthly return on portfolio 7

r8

monthly return on portfolio 8

r9

monthly return on portfolio 9

r10

monthly return on portfolio 10 (large firms)

rf

risk free rate (return on 3-month T-bill)

cons

real per capita consumption growth based on total US personal consumption expenditures (nondurables and services)

Source

Center for research in security prices.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 5.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Us States Production

Description

a panel of 48 observations from 1970 to 1986

number of observations : 816

observation : regional

country : United States

Usage

data(Produc)

Format

A dataframe containing :

state

the state

year

the year

pcap

private capital stock

hwy

highway and streets

water

water and sewer facilities

util

other public buildings and structures

pc

public capital

gsp

gross state products

emp

labor input measured by the employment in non–agricultural payrolls

unemp

state unemployment rate

Source

Munnell, A. (1990) “Why has productivity growth declined? Productivity and public investment”, New England Economic Review, 3–22.

Baltagi, B. H. and N. Pinnoi (1995) “Public capital stock and state productivity growth: further evidence”, Empirical Economics, 20, 351–359.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Return to Schooling

Description

a panel of 48 observations from 1970 to 1986

number of observations : 5225

observation : individuals

country : United States

Usage

data(RetSchool)

Format

A time series containing :

wage76

wage in 1876

grade76

grade level in 1976

exp76

experience 1n 1976

black

black ?

south76

lived in south in 1976 ?

smsa76

lived in SMSA in 1976 ?

region

region, a factor with levels (un, midatl, enc, wnc, sa, esc, wsc, m, p)

smsa66

lived in SMSA in 1966 ?

momdad14

lived with both parents at age 14 ?

sinmom14

lived with mother only at age 14 ?

nodaded

father has no formal education ?

nomomed

mother has no formal education ?

daded

mean grade level of father

momed

mean grade level of mother

famed

father's and mother's education, a factor with 9 levels

age76

age in 1976

col4

is any 4-year college nearby ?

Source

Kling, Jeffrey R. (2001) “Interpreting Instrumental Variables Estimates of the Return to Schooling”, Journal of Business and Economic Statistics, 19(3), July, 358–364.

Dehejia, R.H. and S. Wahba (2002) “Propensity-score Matching Methods for Nonexperimental Causal Studies”, Restat, 151–161.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge.

See Also

Schooling, Treatment, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Returns on Standard & Poor's 500 Index

Description

daily observations from 1981–01 to 1991–04

number of observations : 2783

Usage

data(SP500)

Format

A dataframe containing :

r500

daily return S&P500 (change in log index)

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wages and Schooling

Description

a cross-section from 1976

number of observations : 3010

observation : individuals

country : United States

Usage

data(Schooling)

Format

A dataframe containing :

smsa66

lived in SMSA in 1966 ?

smsa76

lived in SMSA in 1976 ?

nearc2

grew up near 2-yr college ?

nearc4

grew up near 4-yr college ?

nearc4a

grew up near 4-year public college ?

nearc4b

grew up near 4-year private college ?

ed76

education in 1976

ed66

education in 1966

age76

age in 1976

daded

dad's education (imputed avg if missing)

nodaded

dad's education imputed ?

momed

mother's education

nomomed

mom's education imputed ?

momdad14

lived with mom and dad at age 14 ?

sinmom14

single mom at age 14 ?

step14

step parent at age 14 ?

south66

lived in south in 1966 ?

south76

lived in south in 1976 ?

lwage76

log wage in 1976 (outliers trimmed)

famed

mom-dad education class (1-9)

black

black ?

wage76

wage in 1976 (raw, cents per hour)

enroll76

enrolled in 1976 ?

kww

the kww score

iqscore

a normed IQ score

mar76

married in 1976 ?

libcrd14

library card in home at age 14 ?

exp76

experience in 1976

Source

National Longitudinal Survey of Young Men (NLSYM).

Card, D. (1995) Using geographical variation in college proximity to estimate the return to schooling in Christofides, L.N., E.K. Grant and R. Swidinsky (1995) Aspects of labour market behaviour : essays in honour of John Vanderkamp, University of Toronto Press, Toronto.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 5.

See Also

RetSchool, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Solow's Technological Change Data

Description

annual observations from 1909 to 1949

number of observations : 41

observation : country

country : United States

Usage

data(Solow)

Format

A time series containing :

q

output

k

capital/labor ratio

A

index of technology

Source

Solow, R. (1957) “Technical change and the aggregate production function”, Review of Economics and Statistics, 39, 312-320.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometrics0000haya, Table F7.2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Visits to Lake Somerville

Description

a cross-section from 1980

number of observations : 659

observation : individuals

country : United States

Usage

data(Somerville)

Format

A dataframe containing :

visits

annual number of visits to lake Somerville

quality

quality ranking score for lake Somerville

ski

engaged in water–skiing at the lake ?

income

annual household income

feeSom

annual user fee paid at lake Somerville ?

costCon

expenditures when visiting lake Conroe

costSom

expenditures when visiting lake Somerville

costHoust

expenditures when visiting lake Houston

Source

Seller, Christine, John R. Stoll and Jean–Paul Chavas (1985) “Valuation of empirical measures of welfare change : a comparison of nonmarket techniques”, Land Economics, 61(2), May, 156–175.

Gurmu, Shiferaw and Pravin K. Trivedi (1996) “ Excess zeros in count models for recreational trips”, Journal of Business and Economics Statistics, 14(4), October, 469–477.

Santos Silva, Jao M. C. (2001) “A score test for non–nested hypotheses with applications to discrete data models”, Journal of Applied Econometrics, 16(5), 577–597.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20. Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 6.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Effects on Learning of Small Class Sizes

Description

a cross-section from 1985-89

number of observations : 5748

observation : individuals

country : United States

Usage

data(Star)

Format

A dataframe containing :

tmathssk

total math scaled score

treadssk

total reading scaled score

classk

type of class, a factor with levels (regular,small.class,regular.with.aide)

totexpk

years of total teaching experience

sex

a factor with levels (boy,girl)

freelunk

qualified for free lunch ?

race

a factor with levels (white,black,other)

schidkn

school indicator variable

Source

Project STAR:

Description from 2001-06-02. Description from 2011-06-18.

References

Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 11.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Strike Duration Data

Description

a cross-section from 1968 to 1976

number of observations : 62

country : United States

Usage

data(Strike)

Format

A dataframe containing :

duration

strike duration in days

prod

unanticipated output

Source

Kennan, J. (1985) “The duration of contract strikes in U.S. manufacturing”, Journal of Econometrics, 28, 5-28.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometrics0000haya, Table F22.1.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Strikes Duration

Description

a cross-section from 1968 to 1976

number of observations : 566

country : United States

Usage

data(StrikeDur)

Format

A dataframe containing :

dur

duration of the strike in days

gdp

measure of stage of business cycle (deviation of monthly log industrial production in manufacturing from prediction from OLS on time, time-squared and monthly dummies)

Source

Kennan, J. (1985) “The Duration of Contract strikes in U.S. Manufacturing”, Journal of Econometrics, 28, 5-28.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 574–5 and 582.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Number of Strikes in Us Manufacturing

Description

monthly observations from 1968(1) to 1976 (12)

number of observations : 108

observation : country

country : United States

Usage

data(StrikeNb)

Format

A time series containing :

strikes

number of strikes (number of contract strikes in U.S. manufacturing beginning each month)

output

level of economic activity (measured as cyclical departure of aggregate production from its trend level)

time

a time trend from 1 to 108

Source

Kennan, J. (1985) “The Duration of Contract strikes in U.S. Manufacturing”, Journal of Econometrics, 28, 5-28.

Cameron, A.C. and Trivedi P.K. (1990) “Regression Based Tests for Overdispersion in the Poisson Model”, Journal of Econometrics, December, 347-364.

References

Cameron, A.C. and Trivedi P.K. (1998) Regression analysis of count data, Cambridge University Press, https://cameron.econ.ucdavis.edu/racd/racddata.html, chapter 7.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

The Penn Table

Description

a panel of 125 observations from 1960 to 1985

number of observations : 3250

observation : country

country : World

Usage

data(SumHes)

Format

A dataframe containing :

year

the year

country

the country name (factor)

opec

OPEC member ?

com

communist regime ?

pop

country's population (in thousands)

gdp

real GDP per capita (in 1985 US dollars)

sr

saving rate (in percent)

Source

Summers, R. and A. Heston (1991) “The Penn world table (mark 5): an expanded set of international comparisons, 1950-1988”, Quarterly Journal of Economics, 29, 229-256.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 5, 358-363.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Interest Rate, GDP and Inflation

Description

quarterly observations from 1950-1 to 1996-4

number of observations : 188

observation : country

country : Canada

Usage

data(Tbrate)

Format

A time series containing :

r

the 91-day treasury bill rate

y

the log of real GDP

pi

the inflation rate

Source

CANSIM database of Statistics Canada.

References

Davidson, R. and James G. MacKinnon (2004) Econometric Theory and Methods, New York, Oxford University Press, chapter 2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Households Tobacco Budget Share

Description

a cross-section from 1995-96

number of observations : 2724

observation : individuals

country : Belgium

Usage

data(Tobacco)

Format

A dataframe containing :

occupation

a factor with levels (bluecol, whitecol, inactself), the last level being inactive and self-employed

region

a factor with levels (flanders, wallon, brussels)

nkids

number of kids of more than two years old

nkids2

number of kids of less than two years old

nadults

number of adults in household

lnx

log of total expenditures

stobacco

budget share of tobacco

salcohol

budget share of alcohol

age

age in brackets (0-4)

Source

National Institute of Statistics (NIS), Belgium.

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons, chapter 7.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Stated Preferences for Train Traveling

Description

a cross-section from 1987

number of observations : 2929

observation : individuals

country : Netherland

Usage

data(Train)

Format

A dataframe containing :

id

individual identifier

choiceid

choice identifier

choice

one of choice1, choice2

pricez

price of proposition z (z=1,2) in cents of guilders

timez

travel time of proposition z (z=1,2) in minutes

comfortz

comfort of proposition z (z=1,2), 0, 1 or 2 in decreasing comfort order

changez

number of changes for proposition z (z=1,2)

Source

Meijer, Erik and Jan Rouwendal (2005) “Measuring welfare effects in models with random coefficients”, Journal of Applied Econometrics, forthcoming.

Ben–Akiva, M., D. Bolduc and M. Bradley (1993) “Estimation of travel choice models with randomly distributed values of time”, Transportation Research Record, 1413, 88–97.

Carson, R.T., L. Wilks and D. Imber (1994) “Valuing the preservation of Australia's Kakadu conservation zone”, Oxford Economic Papers, 46, 727–749.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Statewide Data on Transportation Equipment Manufacturing

Description

a cross-section

number of observations : 25

observation : regional

country : United States

Usage

data(TranspEq)

Format

A dataframe containing :

state

state name

va

output

capital

capital input

labor

labor input

nfirm

number of firms

Source

Zellner, A. and N. Revankar (1970) “Generalized production functions”, Review of Economic Studies, 37, 241-250.

References

Greene, W.H. (2003) Econometric Analysis, Prentice Hall, https://archive.org/details/econometrics0000haya, Table F9.2.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Evaluating Treatment Effect of Training on Earnings

Description

a cross-section from 1974

number of observations : 2675

country : United States

Usage

data(Treatment)

Format

A dataframe containing :

treat

treated ?

age

age

educ

education in years

ethn

a factor with levels ("other", "black", "hispanic")

married

married ?

re74

real annual earnings in 1974 (pre-treatment)

re75

real annual earnings in 1975 (pre-treatment)

re78

real annual earnings in 1978 (post-treatment)

u74

unemployed in 1974 ?

u75

unemployed in 1975 ?

Source

Lalonde, R. (1986) “Evaluating the Econometric Evaluations of Training Programs with Experimental Data”, American Economic Review, 604–620.

Dehejia, R.H. and S. Wahba (1999) “Causal Effects in Nonexperimental Studies: reevaluating the Evaluation of Training Programs”, JASA, 1053–1062.

Dehejia, R.H. and S. Wahba (2002) “Propensity-score Matching Methods for Nonexperimental Causal Studies”, Restat, 151–161.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 889–95.

See Also

RetSchool, Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Choice of Brand for Tuna

Description

a cross-section

number of observations : 13705

observation : individuals

country : United States

Usage

data(Tuna)

Format

A dataframe containing :

hid

individuals identifiers

id

purchase identifiers

choice

one of skw (Starkist water), cosw (Chicken of the sea water), pw (store–specific private label water), sko (Starkist oil), coso (Chicken of the sea oil)

price.z

price of brand z

Source

Kim, Byong–Do, Robert C. Blattberg and Peter E. Rossi (1995) “Modeling the distribution of price sensitivity and implications for optimal retail pricing”, Journal of Business Economics and Statistics, 13(3), 291.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

US Finance Industry Profits

Description

A data.frame giving the profits of the finance industry in the United States as a proportion of total corporate domestic profits.

Usage

data(USFinanceIndustry)

Format

A data.frame with the following columns:

year

integer year starting with 1929

CorporateProfitsAdj

Corporate profits with inventory valuation and capital consumption adjustments in billions of current (not adjusted for inflation) US dollars

Domestic

Domestic industries profits in billions

Financial

Financial industries profits in billions

Nonfinancial

Nonfinancial industries profits in billions

restOfWorld

Profits of the "Rest of the world" in their contribution to US Gross Domestic Product in billions

FinanceProportion

= Financial/Domestic

Details

This is extracted from Table 6.16 of the National Income and Product Accounts (NIPA) compiled by the Bureau of Economic Analysis of the United States federal government. This table comes in four parts, A (1929-1947), B (1948-1987), C (1987-2000), and D (1998-present). Parts A, B, C and D contain different numbers of data elements, but the first five have the same names and are the only ones used here. The overlap between parts C and D (1998-2000) have a root mean square relative difference of 0.7 percent; there were no differences between the numbers in the overlap period between parts B and C (1987).

This was created using the following command:

demoDir <- system.file('demoFiles', package='Ecdat') demoCsv <- dir(demoDir, pattern='csv$', full.names=TRUE)

nipa6.16 <- Ecfun::readNIPA(demoCsv) USFinanceIndustry <- as.data.frame(nipa6.16) names(USFinanceIndustry) <- c('year', 'CorporateProfitsAdj', 'Domestic', 'Financial', 'Nonfinancial', 'restOfWorld') USFinanceIndustry$FinanceProportion <- with(USFinanceIndustry, Financial/Domestic)

Source

https://www.bea.gov: Under "U.S. Economic Accounts", first select "Corporate Profits" under "National". Then next to "Interactive Tables", select, "National Income and Product Accounts Tables". From there, select "Begin using the data...". Under "Section 6 - income and employment by industry", select each of the tables starting "Table 6.16". As of February 2013, there were 4 such tables available: Table 6.16A, 6.16B, 6.16C and 6.16D. Each of the last three are available in annual and quarterly summaries. The USFinanceIndustry data combined the first 4 rows of the 4 annual summary tables.

See Also

readNIPA

Examples

data(USFinanceIndustry)
plot(FinanceProportion~year, USFinanceIndustry, type='b',
     ylim=c(0, max(FinanceProportion, na.rm=TRUE)),
     xlab='', ylab='', las=1, cex.axis=2, bty='n', lwd=2,
     col='blue')

# Write to a file for Wikimedia Commons
## Not run: 
if(FALSE){
  svg('USFinanceIndustry.svg')
  plot(FinanceProportion~year, USFinanceIndustry, type='b',
     ylim=c(0, max(FinanceProportion, na.rm=TRUE)),
     xlab='', ylab='', las=1, cex.axis=2, bty='n', lwd=2,
     col='blue')
  dev.off()
  }
  
## End(Not run)

US GDP per capita with presidents and wars

Description

It is commonly claimed that Franklin Roosevelt (FDR) did not end the Great Depression: World War II (WW2) did. This is supported by the 10.6 percent growth per year in real Gross Domestic Product (GDP) per capita seen in the standard GDP estimates from 1940 to 1945. It is also supported by the rapid decline in unemployment during the war.

However, no comparable growth spurts in GDP per capita catch the eye in a plot of log(GDP per capita) from 1790 to 2024, whether associated with a war or not, using data from Measuring Worth. The only other features of that plot that seem visually comparable are the economic disaster of Herbert Hoover's presidency (when GDP per capital fell by 10 percent per year, 1929-1932), the impressive growth of the US economy during the first seven years of Franklin Roosevelt's presidency (6.4 percent per year, 1933-1940), and the post-World War II recession (when GDP per capita fell by 7.9 percent per year, 1945-1947). (NOTE: The web site for Measuring Worth, https://measuringworth.com/ still works, but has not always been maintained to current internet security standards. Therefore, the link is provided here in text but not as a link.)

Closer inspection of this plot suggests that the US economy has generally grown faster after FDR than before. This might plausibly be attributed to "The Keynesian Ascendancy 1939-1979".

Unemployment dropped during the First World War as it did during WW2. Comparable unemployment data are not available for the U.S. during other major wars, most notably the American Civil War and the Mexican-American War.

This data set provides a platform for testing the effects of presidency, war, and Keynes. It does this by combining the numbers for US population and real GDP per capital dollars from Measuring Worth with the presidency and a list of major wars and an estimate of the battle deaths by year per million population. (As noted above, the web address for measuring worth, https://measuringworth.com/, often gives security warnings but still seems to provide the data as before.)

Usage

data(USGDPpresidents)

Format

A data.frame containing 259 observations on the following variables:

Year

integer: the year, c(seq(1610, 1770, 10), 1774:2024)

CPI

Numeric: U. S. Consumer Price Index per Officer and Williamson (2022), starting in 1774. Average 1982-84 = 100.

GDPdeflator

numeric: Implicit price deflators for Gross Domestic Product with 2017 = 100 per Williamson (2025).

population.K

integer: US population in thousands.

Population figures for 1610 to 1780 came from Springston (2013). The rest came from Johnston and Williamson. (The early population figures reflect only the European settlers in the British colonies that eventually became the US.)

realGDPperCapita

numeric: real Gross Domestic Product (GDP) per capita in 2017 dollars since 1790.

Real GDP = population.K*realGDPperCapita, in thousands.

Current or nominal GDPperCapita = realGDPperCapita*GDPdeflator/100.

executive

ordered: Crown of England through 1774, followed by the "ContinentalCongress" and the "ArticlesOfConfederation" until Washington, who became President under the current base constitution in 1789. Two nineteenth century presidents are not listed here (William Henry Harrison and James A. Garfield), because they died so soon after inauguration that any contribution they made to the economic growth of the nation might seem too slight to measure accurately in annual data like this; their contributions therefore appear combined with their replacements (John Tyler and Chester A. Arthur, respectively). The service of two other presidents is officially combined here: "Taylor-Fillmore" refers to the 16 months served by Zachary Taylor with the 32 months of Millard Fillmore. These modifications make Barack Obama number 41 on this list, even though he's the 44th president of the U.S.

war

ordered: This lists the major wars in US history by years involving active hostilities. A war is "major" for present purposes if it met two criteria:

(1) It averaged at least 10 battle deaths per year per million US population.

(2) It was listed in one of two lists of wars: For wars since 1816, it must have appeared in the Correlates of War. For wars between 1790 and 1815, it must have appeared in the Wikipedia "List of wars involving the United States".

The resulting list includes a few adjustments to the list of wars that might come readily to mind for people moderately familiar with US history.

A traditional list might start with the American Revolution, the War of 1812, the Mexican-American war, the Civil War, the Spanish-American war, World Wars I and II, Korea, and Vietnam. In addition, the Northwest Indian War involved very roughly 30 battle deaths per year per million population 1785-1795. This compares with the roughly 100 battle deaths per year 1812-1815 for the War of 1812.

For present purposes, the Spanish-American War is combined with the lesser-known American-Philippine War: The latter involved 50 percent more battle deaths but over a longer period of time and arguably with less impact on the stature of the US as a growing world power. However, its magnitude suggest it might have impacted the US economy in a way roughly comparable to the Spanish-American war. The two are therefore listed here together as "Spanish-American-Philippine" war.

The Correlates of War (COW) data include multiple US uses of military force during the Vietnam War era. It starts with "Vietnam Phase 1", 1961-65, with 506 battle deaths in the COW data base. It includes the "Second Laotian" war phases 1 and 2, plus engagement with a "Communist Coalition" and Khmer Rouge as well as actions in the Dominican Republic and Guatemala. The current data.frame includes only "Vietnam", referring primarily to COW's "Vietnam War, Phase 2", 1965-1973. The associated battle deaths include battle deaths from these other, lesser concurrent conflicts.

The COW data currently ends in 2007. However, the post-2000 conflicts in Afghanistan and Iraq averaged less than 1,000 battle deaths per year or roughly 3 battle deaths per year per million population. This is below the threshold of 10 battle deaths per year per million population. This in turn suggests that any impact of those conflicts on the US economy might be small and difficult to estimate.

battleDeaths

numeric: Numbers of battle deaths by year estimated by allocating to the different years the totals reported for each major war in proportion to the number of days officially in conflict each year. The totals were obtained (in August-September 2015) from The Correlates of War data for conflicts since 1816 and from Wikipedia for previous wars back to 1774, as noted above.

battleDeathsPMP

numeric: battle deaths per million population = 1000*battleDeaths/population.K.

Keynes

integer taking the value 1 between 1939 and 1979 and 0 otherwise, as suggested by the section entitled "The Keynesian Ascendancy 1939-1979" in the Wikipedia article on John Maynard Keynes.

unemployment

Estimated US unemployment rate in percent per the sources cited in the Historical unemployment rate charts section of the Wikipedia article on Unemployment in the United States .

unempSource

ordered giving the source for US unemployment:

1610-1799

<NA>

1800-1889

Lebergott

1890-1929

Romer

1930-1939

Coen

1940-present

BLS

Clearly, the more recent numbers should be more accurate.

fedReceipts, fedOutlays, fedSurplus

Receipts and Outlays of the US federal government in millions of current dollars.

For data beginning with 1901, these are from the US federal budget from The White House (2022). Earlier data are from series Y 335-337 in US Census Bureau (1975). As of 2022-02-22 the data from The White House included aggregations for 1789-1849 and 1850-1900, which matched the totals of Y 335-337 for those two sets of years. The numbers from 1901 to 1933 are the same in both sources.

On 2022-02-22, we used The White House (2022) for the more recent numbers with one exception: Between 1976 and 1977 the fiscal year was changed from starting July 1 to October 1. July, August, and September, 1976, is called the "transitional quarter", and has been deleted from this dataset.

On 2025-01-22, the comparable data was found on a different web address but seemed to be largely the same except that it said it was updated to 2023-03-28, just over a month after the previous update. That gave data starting in 2022 as "estimates". Since we could not find better numbers, we used those.

NOTES:

The numbers for 1843 are for only the first half of the year, January 1 through June 30. This explains why the numbers for 1843 are only roughly half of the corresponding values for 1844 and 1845.

Also, the numbers for 1791 are actually for 1789-1791. However, those numbers seem comparable to those for 1792 and 1793, so it is listed as only for one year rather than three.

fedDebt

US federal government debt in current dollars per FiscalData (2025). This matches Y 338 in United States Census Bureau (1975) 1921-1939 but not earlier, and Y 338 ends with 1939. Between 1921 and 1939 these numbers are as of June 30. Between 1843 and 1920 they are as of July 1. The earlier numbers are as of January 1.

These numbers are NOT a simple cumsum of fedSurplus. It's not clear the sources of the discrepancies, but the following seem likely: First, the published budget may not include interest on the national debt. Second, there are likely expenditures / outlays that are "Off-budget" and perhaps otherwise hidden from the public.

FiscalData (2025) includes debt for both January 1 (20 million) and July 1 (33 million) for 1843. For present purposes, we omit the January 1 number. This overstates the volatility of the national debt during that period, showing it rising from 14 million in 1842 (January 1) to 33 million in 1843 (July 1), being 18 not 12 months. The alternative would be to delete the 33 million, but that would understate the volatility of the debt during that period.

Prior to 1844, the national debt was reported for January 1. Between 1843 and 1920, it was reported for July 1. From 1921 to 1976, it was reported for June 28, 29 or 30, usually for June 30; four years in that period it was reported for June 29 and once for June 28. Since 1977, it has been reported for September 28, 29 or 30, usually for September 30, only once for September 28 and once for September 29.

fedReceipts_pGDP, fedOutlays_pGDP, fedSurplus_pGDP, fedDebt_pGDP

numeric = fedReceipts, fedOutlays, fedSurplus, and fedDebt as a portion of GDP, which is population.K * realGPDperCapita / (.01*GDPdeflator).

For the single year 1843, fedReceipts, fedOutlays, and fedSurplus were for only the first six months; to compute *_pGDP for these numbers for 1843 only, the denominator was cut in half.

Details

rownames(USGDPpresidents) = Year

Author(s)

Spencer Graves

Source

Robert M. Coen (1973) Labor Force and Unemployment in the 1920's and 1930's: A Re-Examination Based on Postwar Experience", The Review of Economics and Statistics, 55(1): 46-55.

FiscalData (2024) "Historical Debt Outstanding", accessed 2025-01-22.

Louis Johnston and Samuel H. Williamson, "What Was the U.S. GDP Then?", Measuring Worth, accessed 2022-02-22. (NOTE: This came from https://www.measuringworth.org/usgdp/. this web link generally works as of 2022-02-22. However, in the past it has sometimes returned a warning, e.g., "SSL certificate problem". The web site seems to be good but not maintained to current security standards.)

Stanley Lebergott (1964). Manpower in Economic Growth: The American Record since 1800. Pages 164-190. New York: McGraw-Hill. Cited from Wikipedia, "Unemployment in the United States", accessed 2016-07-08.

Lawrence H Officer and Samuel H. Williamson, 'The Annual Consumer Price Index for the United States, 1774-Present,' MeasuringWorth, 2022-02-22.

Christina Romer (1986). "Spurious Volatility in Historical Unemployment Data", The Journal of Political Economy, 94(1): 1-37.

Sarkees, Meredith Reid; Wayman, Frank (2010). "The Correlates of War Project: COW War Data, 1816 - 2007 (v4.0)", accessed 2015-09-02.

The White House (2022). On 2025-08-22, I saw "Historical Tables" in 3 places on that page. I clicked on the bottom one and got, "BUDGET-2026-HIST.xlsx". The file I got doing this on 2025-01-22 included "Table 1.1-Summary of Receipts, Outlays, and Surpluses or Deficits (-): 1789-2026" included budget forecasts. The version of this table I got 2025-08-22 included data through 2024 but no forecasts.

United States Census Bureau (1975) Bicentennial Edition: Historical Statistics of the United States, Colonial Times to 1970, Part 2. Chapter Y. Government, accessed 2022-02-22.

Wikipedia, "List of wars involving the United States", accessed 2015-09-13.

Wikipedia, "Unemployment in the United States". See also https://en.wikipedia.org/wiki/User_talk:Peace01234#Unemployment_Data. Accessed 2016-07-08.

The unemployment data since 1940 are from series LNS14000000 from the Current Population Survey. These data are available as a monthly series from the Current Population Survey of the Bureau of Labor Statistics.

Chuck Springston, "Population of the 13 Colonies 1610-1790", October 28, 2013

Samuel H. Williamson, "What Was the U.S. GDP Then?" MeasuringWorth, 2025

Examples

data(USGDPpresidents)
##
## FUNCTION TO plot GDP, Presidents and Wars 
## 
plotUSGPDpresidents <- function(y, Ylab, Scale=1, 
        Ylim=NA, Log='y', x='Year', Xmin=NA, Type='l', 
        epocs = c(1929, 1933, 1945), epocy=c(.2, .8), 
        epocNames = c('Hoover', 'FDR'), epocex=c(0.9, 1.1), 
        war='war', warShade=c(lty='dotted', col='grey'), 
        Data=USGDPpresidents, ...){
  ##
  ## 1. y
  ##
  Y <- (Scale* Data[, y])
  if(any(is.na(Ylim))){
    if(is.na(Ylim[1])) {
      if(length(grep('y',Log)>0)){
        Y0 <- (Y<=0)
        n0 <- sum(Y0, na.rm=TRUE)
        if(n0>0){
          cat(n0, ' nonpositive observations ignored/n')
          Y[Y0] <- NA
        }
      } 
      Ylim[1] <- min(Y, na.rm=TRUE)
    }
    if(length(Ylim)<2 || is.na(Ylim[2])){
      Ylim[2] <- max(Y, na.rm=TRUE)
    }
  }
  ##
  ## 2. Xmin > Xlim
  ##
  if(is.na(Xmin)){
    imin <- which.max(!is.na(Y))
    Xmin <- Data[imin, x]
  }
  Xlim <- c(Xmin, max(Data[, x]))
  ##
  ## 3. plot
  ##
  plot(Data[, x], Y, log=Log, type=Type, 
       xlim=Xlim, xlab='', ylim=Ylim,
       ylab=Ylab, las=1, ...)  
  ##
  ## 4. epocs
  ##
  abline(v=epocs, lty='dashed')
  if(length(grep('y',Log)>0)){
    lYlim <- log(Ylim)
    yep <- exp(epocy*lYlim[1]+(1-epocy)*lYlim[2])
  } else {
    yep <- (epocy*Ylim[1]+(1-epocy)*Ylim[2])
  }
  for(i in 1:length(epocy)){
    ix <- mean(epocs[i+0:1])
    text(ix, yep[i], epocNames[i], srt=90, 
         cex=epocex[i])
  }
  ##
  ## 5. wars
  ##
  if(!is.null(war) && !is.na(war) &&
     !is.na(match(war, names(Data))))  {
    selWar <- (Data[, war]!='')
    abline(v=Data[selWar, x], lty=warShade['lty'], 
           col=warShade['col'])
  }
}
##
##** Plot the first four variables
##
plotUSGPDpresidents('CPI', Ylab='Consumer Price Index')
plotUSGPDpresidents('GDPdeflator', Ylab='GDP deflator')
plotUSGPDpresidents('population.K', Ylab='population (M)', 
                   Scale=0.001)
plotUSGPDpresidents('realGDPperCapita', 
                   Ylab='GDP per capita (2017K$)', Scale=0.001)

##
##** Table exective and war
##
table(USGDPpresidents[, 'executive'])
table(USGDPpresidents[, 'war'])

##
##** plot battleDeaths 
##** battledeathsPMP = per million population
##
plotUSGPDpresidents('battleDeaths', Ylab='battle deaths (K)', 
                   Scale=0.001, lwd=3)

(MAw <- grep('Mex', USGDPpresidents[, 'war']))
USGDPpresidents[MAw,]

plotUSGPDpresidents('battleDeathsPMP', 
                   Ylab='battle deaths per million pop', lwd=3)
##
##** plot Keynes
##
plotUSGPDpresidents('Keynes', Log='', Ylab='Keynes')
selKeynes <- (USGDPpresidents[, 'Keynes']==1)
range(USGDPpresidents[selKeynes, 'Year'])
##
##** plot unemployment
##
plotUSGPDpresidents('unemployment', Ylab='unemployment (%)')
# Estimated US unemployment rate in percent
# per the sources cited in the section on 
# "Historical unemployment rate charts"
# in the Wikipedia article on 
# "Unemployment in the United States"

# table unemployment source
table(USGDPpresidents[, 'unempSource'])

##
##** plot budget analyses
##
plotUSGPDpresidents('fedReceipts', Ylab="fed receipts ($M)")
plotUSGPDpresidents("fedReceipts", Ylab="fed receipts ($B)", 
                   Scale=0.001)
abline(h=1)
plotUSGPDpresidents("fedOutlays", Ylab="fed outlays ($B)", 
                   Scale=0.001)
abline(h=1)

plotUSGPDpresidents("fedSurplus", Ylab="fed outlays ($B)",
                   Log='', Scale=0.001)

Surplus <- with(USGDPpresidents, fedReceipts - fedOutlays)

rSurp <- with(USGDPpresidents, fedSurplus/Surplus)
plot(USGDPpresidents[, 'Year'], rSurp)
# Discrepancies less than 1 percent

plotUSGPDpresidents('fedDebt', 'fed debt ($B)',
                   Scale=1e-9)

plotUSGPDpresidents('fedReceipts_pGDP', 
                   'fed receipts % of GDP', Scale=100)
plotUSGPDpresidents('fedOutlays_pGDP', 
                   'fed outlays % of GDP', Scale=100)
plotUSGPDpresidents('fedSurplus_pGDP', 
                   'fed surplus % of GDP', Scale=100, Log='')

plotUSGPDpresidents('fedDebt_pGDP', 
                   'fed debt % of GDP', Scale=100)
(debtPrng <- range(USGDPpresidents[, 'fedDebt_pGDP'], na.rm=TRUE))
plotUSGPDpresidents('fedDebt_pGDP', 
                   'fed debt % of GDP', Scale=100, 
                   Ylim=c(1, 100*debtPrng[2]))
abline(h=100)

US Postal Service

Description

Numbers of post offices in the US from 1789 to 2020 with their income and expenses in current dollars and proportion of the federal government and of Gross Domestic Product (GDP). Also includes the number of pieces of mail, numbers of periodicals, pieces and periodicals per person, and cost coverage of periodicals for selected years.

It would be interesting to find the total value of the subsidies for newspapers and other periodicals as a proportion of the budgets of the USPS and the federal government as well as of GDP. That is currently absent from the data consulted to produce this.

Usage

data(USPS)

Format

A data.frame containing 232 observations on the following variables:

Year

integer: the year: 1789:2020

Income, Expenses

Income and expenses in millions of current dollars, per Historian (2022).

Income_pFed, Expenses_pFed

Income and Expenses as a proportion of USGDPpresidents[, 'fedReceipts'] and USGDPpresidents[, 'fedOutlays'], respectively.

Income_pGDP, Expenses_pGDP

Income and Expenses as a proportion of GDP, per MeasuringWorth.

Income_cap, Expenses_cap

Income and Expenses per capita in current dollars = Income and Expenses divided by 1000 * USGDPpresidents[, 'population.K'].

realIncome_cap, realExpenses_cap

Income and Expenses per capita in constant 2012 dollars = Income_cap and Expenses_cap divided by USGDPpresidents[, 'GDPdeflator'].

postOffices

Number of post offices per Historian (2022).

KpopPerPostOffice

US population in thousands per post office: USGDPpresidents[, 'population.K'] divided by postOffices.

piecesOfMail, periodicals

numeric: Millions of pieces of mail handled and periodicals mailed. "Pieces of mail"" are from Historian (2022). "Periodicals" are from Historian (2010).

piecesOfMailPerCap, periodicalsPerCap

piecesOfMail and periodicals handled per capita (per human in the US) per year.

costCoveragePeriodicals

Cost coverage of periodicals, per Historian (2010). This is available here only since 1960, though Historian (2010) gave a general outline of these numbers. This included saying, "In 1966, the percentage of its own costs covered by second-class mail (or 'cost coverage'), including the subsidy, was 35 percent [reported as 36 percent here]. Its real coverage was 24 percent." The narrative noted that during parts of the nineteenth century the actual rate was zero. Sometimes it was zero only within county. Sometimes advertising was charged a higher rate than news.

Other than numbers for the period since 1960, we note the coverage in 1951 as 20 percent, based on the following comment:

"In February 1951, in a special message to Congress, President Harry S. Truman argued at length for a rate increase: 'In fiscal year 1952 . . . newspaper and magazine publishers will have 200 million dollars – or 80 percent – of their postal costs paid for them by the general public.'"

Details

rownames(USPS) = year

Data used by McChesney and Nichols (2021-12-13) To Protect and Extend Democracy, Recreate Local News Media (Freepress.net, p. 6, note 10) to estimate that newspaper subsidies averaged roughly 0.216 percent of GDP between 1840 and 1844.

Author(s)

Spencer Graves

Source

Historian (2010-06) Postage Rates for Periodicals: A Narrative History, accessed 2022-04-29.

Historian (2022-02) Pieces of Mail Handled, Number of Post Offices, Income, and Expenses Since 1789.

References

Robert W. McChesney and John Nichols (2010) The Death and Life of American Journalism (Nation Books, pp. 310-311) describe how they computed 0.216 as an estimate of the percent of national income (Gross Domestic Product, GDP) devoted to newspaper subsidies, 1840-1844. The numbers in the current dataset seem essentially equivalent but new and therefore perhaps more accurate. With these numbers, we got 0.209 percent of GDP rather than their 0.216 percent.

Examples

##
## plot Expenses as a percent of the 
## federal budget and of GDP 
##
data(USPS)
plot(Expenses_pFed~Year, USPS, type='l')
plot(Expenses_pGDP~Year, USPS, type='l')
plot(100*periodicals/piecesOfMail~Year, 
      USPS, type='l', ylab='', 
      main='periodicals as percent of mail')
      
# Select a year 
# as a charcter string not a number:
USPS['1850',]

##
## Plot Expenses_pGDP with 
## USGDPpresidents[, 'fedOutlays_pGDP']
##
str(yrs2 <- intersect(USPS$Year, 
              USGDPpresidents$Year))
yrs2a <- as.character(yrs2)

str(USPS_fed <- cbind(USPS[yrs2a, "Expenses_pGDP"], 
      USGDPpresidents[yrs2a, "fedOutlays_pGDP"]))

matplot(yrs2, USPS_fed, log='y', 
  ylab='', las=1, type='l', xlab='')
abline(v=c(1840, 1844), lty='dotted', col='grey')
text(1842, 6e-3, cex=.7,
  'McChesney & Nichols analysis', srt=90, col='grey')

abline(v=c(1861, 1865), lty='dotted', col='grey')
text(1863, 6e-3, 'Civil War', srt=90, col='grey')
sel1 <- (USGDPpresidents$war=='World War I')
(yr1 <- USGDPpresidents$Year[sel1])
abline(v=yr1, col='grey', lty='dotted')
text(mean(yr1), 2e-3, 'WWI', col='grey', srt=90)

sel2 <- (USGDPpresidents$war=='World War II')
(yr2 <- range(USGDPpresidents$Year[sel2]))
abline(v=yr2, col='grey', lty='dotted')
text(mean(yr2), 2e-3, 'WWII', col='grey', srt=90)

abline(h=c(.001, .01, .1), lty='dotted', col='grey')
legend("bottomright", 
    c('USPS Expenses_pGDP', 'fedOutlays_pGDP'), 
    col=1:2, lty=1:2, bty='n')

Official Secrecy of the United States Government

Description

Data on classification activity of the United States government.

Fitzpatrick (2013) notes that the dramatic jump in derivative classification activity (DerivClassActivity) that occurred in 2009 coincided with "New guidance issued to include electronic environment". Apart from the jump in 2009, the DerivClassActivity tended to increase by roughly 12 percent per year (with a standard deviation of the increase in the natural logarithm of DerivClassActivity of 0.18).

Usage

data(USclassifiedDocuments)

Format

A dataframe containing :

year

the calendar year

OCAuthority

Number of people in the government designated as Original Classification Authorities for the indicated year.

OCActivity

Original classification activity for the indicated year: These are the number of documents created with an original classification, i.e., so designated by an official Original Classification Authority.

TenYearDeclass

Percent of OCActivity covered by the 10 year declassification rules.

DerivClassActivity

Derivative classification activity for the indicated year: These are the number of documents created that claim another document as the authority for classification.

Details

The lag 1 autocorrelation of the first difference of the logarithms of DerivClassActivity through 2008 is -0.52. However, because there are only 13 numbers (12 differences), this negative correlation is not statistically significant.

Source

Fitzpatrick, John P. (2013) Annual Report to the President for 2012, United States Information Security Oversight Office, National Archives and Record Administration, June 20, 2013. Information Security Oversight Office (ISOO) of the National Archives.

Examples

##
## 1.  plot DerivClassActivity 
##
plot(DerivClassActivity~year, USclassifiedDocuments)
#  Exponential growth?  

plot(DerivClassActivity~year, USclassifiedDocuments, 
     log='y')
# A jump in 2009 as discussed by Fitzpatrick (2013).  
# Otherwise plausibly a straight line.   

##
## 2.  First difference? 
##
plot(diff(log(DerivClassActivity))~year[-1], 
     USclassifiedDocuments)
# Jump in 2009 but otherwise on distribution 

##
## 3.  autocorrelation?  
##
sel <- with(USclassifiedDocuments, 
            (1995 < year) & (year < 2009) )
acf(diff(log(USclassifiedDocuments$
             DerivClassActivity[sel])))
# lag 1 autocorrelation = (-0.52).  
# However, with only 12 numbers, 
# this is not statistically significant.

US incarcerations 1925 onward

Description

Counts of prisoners under the jurisdiction of state and federal correctional authorities in the US. This does not include jail inmates.

Usage

data("USincarcerations")

Format

A data frame with 99 observations on the following 7 variables.

year

an integer vector giving the year c(1925:2023).

stateFedIncarcerees

Total number of incarcerees = maleTotal + femaleTotal.

stateFedIncarcerationRate

incarceration rate = stateFedIncarcerees per 100,000 population.

stateFedMales

Total number of male incarcerees.

stateFedMaleRate

male incarceration rate = maleTotal per 100,000 males in the US population.

stateFedFemales

Total number of female incarcerees.

stateFedFemaleRate

female incarceration rate = femaleTotal per 100,000 females in the US population.

Details

This dataset began as an effort to update File:U.S. incarceration rates 1925 onwards.png on Wikimedia Commons. Conveniently data on these variables was provided in a table for 1925 to 2014. And a description was given of how to update that table using files p*t03.csv and p*t05.csv from Prisoners In 2019.

An initial rationality check was to compute

checkTot <- stateFedIncarcerees - stateFedMales - stateFedFemales

This was 0 except for 1927 and 1973, when it was 637 and 684. The stateFedFemales for 1972:1974 was 6269, 6004, 7389. We replaced 6004 with 6688, which made the checkTot 0 for 1973.

Similar checks for 1927 yielded nothing as obvious. However, the stateFedIncarcerees increased 6.9 percent in 1926 over 1925, and 12.2 and 5.8 percent in the following two years. Subtracting 637 from 109983 for 1927 gave us 109346, which reduced the increase to 11.6 percent for 1927. It's no longer the maximum annual increase prior to 1975.

Next, these numbers were compared with those in p19t03.csv and p19t05.csv, which include numbers of incarcerees and rates per 100,000 population for 2009:2019. The numbers were identical for 2009:2011, but there were several differences for the more recent counts.

For USincarcerations, we used the numbers from p19t03.csv and p19t05.csv, because they seem likely to be more accurate.

However, these numbers include only humans in state and federal prisons. It excludes jails.

Key Statistic: Total correctional population includes a plot of "Total adult correctional population 1980-2016", which does include jails. The data there are available as Total_correctional_population_counts_by_status.csv. Data on these variables covering 2008-2018 are available as cpus1718.csv from "Data tables" at Publication Correctional Populations In The United States, 2017-2018. The data in cpus1718.csv is mostly but not entirely identical to "Total adult correctional population 1980-2016" for 2008-2016, the period of overlap. We therefore used the older data up to 2007 and cpus1718.csv for 2008-2018.

An update to 2023 on 2025-09-01 combined new data from p20stt01.csv and p20stt05.csv from Archive.org with p20stt01.csv and p20stt05.csv from "Prisoners in 2022 - Statistical Tables" and pdrp23t02.csv from "Prisons Report Series: Preliminary Data Release, 2023".

The rates for 2023 were computed by dividing the numbers of incarcerees in pdrp23t02.csv by 2022 population numbers inferred from stateFedIncarcerees/stateFedIncarcerationRate, stateFedMales/stateFedMaleRate, and stateFedFemales/stateFedFemaleRate and adjusted to 2023 by 'pop*exp(median(log(diff(pop))))'. This added 0.63 percent to the 2022 population.

Actual analysis of the jail data is left for another project.

Source

Data from 1925 to 2014 from File:U.S. incarceration rates 1925 onwards.png on Wikimedia Commons, accessed 2020-11-23.

The primary source for the more recent data are files p*t03.csv and p*t05.csv from Prisoners In 2019, accessed 2020-11-23.

p20stt01.csv and p20stt05.csv from Archive.org

p20stt01.csv and p20stt05.csv from "Prisoners in 2022 - Statistical Tables"

pdrp23t02.csv from "Prisons Report Series: Preliminary Data Release, 2023".

Data on jails and community supervision dating back to 1980 are available in Key Statistic: Total correctional population with data on the most recent years available from Publication Correctional Populations In The United States, 2017-2018.

Some time in 2026 or later more recent data should become available. When that happens, it may be desired to update this table to include those numbers – and check for any revisions of earlier numbers.

References

United States incarceration rate.

Examples

data(USincarcerations)

matplot(USincarcerations[1],
  0.001*USincarcerations[c(3, 5, 7)], type='l', 
  xlab='', ylab='incarceration rate (%)')
abline(h=0.5, lty='dotted', col='gray')
lbl <- paste("US incarceration rate", 
  '(percent of the population)', sep='\n')
text(1955, 0.75, lbl)
text(2007, 0.86, 'male', col=2)
text(2007, 0.15, 'female', col=3)

US newspaper revenue 1956 - 2020

Description

Advertising and circulation revenue for US newspapers since 1956 with GDP in billions of current dollars (i.e., not adjusted for inflation) plus ads as a proportion of revenue and revenue as a proportion of US Gross Domestic Product (GDP).

Usage

data("USnewspapers")

Format

A data frame with 65 observations on the following 14 variables.

Year

an integer vector giving the year c(1956:2020).

Ads_currentGdollars, Ads_G2012dollars, Circ_currentGdollars, Circ_G2012dollars, Revenue_currentGdollars, Revenue_G2012dollars

Total newspaper revenue from advertising, circulation, and combined in billions of US dollars, both current and adjusted for inflation to 2012 dollars. The data were compiled from detailed reports until 2012 and estimated since.

AdsProportion

Advertising as a proportion of total revenue.

GDP_nominalG, GDP_G2012

US GDP in billions of dollars, both current and adjusted for inflation to constant 2012 dollars.

newspaperAds_p_GDP

Newspaper advertising revenue as a percent of GDP.

newspapers_p_GDP

Newspaper revenue as a proportion of GDP.

Population_M

US population in millions

RevenuePerCap_nominal

Newspaper revenue per person in current dollars.

RevenuePerCap_2012

Newspaper revenue per person in constant 2012 dollars.

Details

Data used by McChesney and Nichols (2021-12-13) To Protect and Extend Democracy, Recreate Local News Media (Freepress.net, p. 6, note 10) to estimate that newspaper subsidies averaged roughly 0.216 percent of GDP between 1840 and 1844.

Source

Newspaper data from "Newspapers fact sheet" published by the Pew Research Center, accessed 2021-12-18.

GDP data from Measuring Worth, accessed 2021-12-18.

References

McChesney and Nichols (2021-12-13) To Protect and Extend Democracy, Recreate Local News Media (Freepress.net, p. 6, note 10), accessed 2021-12-18.

Newspaper data from "Newspaper fact sheet" published by the Pew Research Center.

GDP data from Measuring Worth.

Examples

data(USnewspapers)

plotNewsRevenue <- function(ys=c(2, 4, 6)){
  ylim. <- range(USnewspapers[ys], na.rm=TRUE)
  xlim. <- range(USnewspapers$Year)
  
  to2013 <- (USnewspapers$Year<2013)

  matplot(USnewspapers$Year[to2013], 
        USnewspapers[to2013, ys], type='l', 
        log='y', xlim=xlim., ylim=ylim., las=1, 
        xlab='', ylab='')
  matlines(USnewspapers$Year[!to2013], col=4:6, 
        USnewspapers[!to2013, ys])

  lnms <- outer(names(USnewspapers[c(2, 4, 6)]),
        c('', '-est'), paste0)

  legend('bottom', lnms, col=1:6, lty=1:6, 
       cex=0.5)
}

plotNewsRevenue()
plotNewsRevenue(c(3, 5, 7))

plot(100*newspapers_p_GDP~Year, USnewspapers, type='l', 
     las=1, xlab='', ylab='newspapers percent of GDP')

plot(RevenuePerCap_nominal~Year, USnewspapers, type='l', 
     las=1, xlab='', ylab='Revenue per capita (nominal)')
plot(RevenuePerCap_2012~Year, USnewspapers, type='l', 
     las=1, xlab='', ylab='Revenue per capita (2012$)')

Standard abbreviations for states of the United States

Description

The object returned by Ecfun::readUSstateAbbreviations() on May 20, 2013.

Usage

data(USstateAbbreviations)

Format

A data.frame containing 10 different character vectors of names or codes for 76 different political entities including the United States, the 50 states within the US, plus the District of Columbia, US territories and other political designation, some of which are obsolete but are included for historical reference.

Name

The standard name of the entity.

Status

description of status, e.g., state / commonwealth vs. island, territory, military mail code, etc.

ISO, ANSI.letters, ANSI.digits, USPS, USCG, Old.GPO, AP, Other

Alternative abbreviations used per different standards. The most commonly used among these may be the 2-letter codes officially used by the US Postal Service (USPS).

Details

This was read from the Wikipedia article on "List of U.S. state abbreviations"

Source

the Wikipedia article on "List of U.S. state abbreviations"

See Also

readUSstateAbbreviations showNonASCII grepNonStandardCharacters subNonStandardCharacters

Examples

##
## to use
##
data(USstateAbbreviations)

##
## to update
##
## Not run: 
USstateAbb2 <- readUSstateAbbreviations()

## End(Not run)

Number of Words in US Tax Law

Description

Thousands of words in US tax law for 1955 to 2015 in 10 year intervals. This includes income taxes and all taxes in the code itself (written by congress) and regulations (written by government administrators). For 2015 only EntireTaxCodeAndRegs is given; for other years, this number is broken down by income tax vs. other taxes and code vs. regulations.

Usage

data(UStaxWords)

Format

A data.frame containing:

year

tax year

IncomeTaxCode

number of words in thousands in the US income tax code

otherTaxCode

number of words in thousands in US tax code other than income tax

EntireTaxCode

number of words in thousands in the US tax code

IncomeTaxRegulations

number of words in thousands in US income tax regulations

otherTaxRegulations

number of words in thousands in US tax regulations other than income tax

IncomeTaxCodeAndRegs

number of words in thousands in both the code and regulations for the US income tax

otherTaxCodeAndRegs

number of words in thousands in both code and regulations for US taxes apart from income taxes.

EntireTaxCodeAndRegs

number of words in thousands in US tax code and regulations

Details

Thousands of words in the US tax code and federal tax regulations, 1955-2015. This is based on data from the Tax Foundation (taxfoundation.org), adjusted to eliminate an obvious questionable observation in otherTaxRegulations for 1965. The numbers of words in otherTaxRegulations was not reported directly by the Tax Foundation but is easily computed as the difference between their Income and Entire tax numbers. This series shows the numbers falling by 48 percent between 1965 and 1975 and by 1.5 percent between 1995 and 2005. These are the only declines seen in these numbers and seem inconsistent with the common concern (expressed e.g., in Moody, Warcholik and Hodge, 2005) about the difficulties of simplifying any governmental program, because vested interest appear to defend almost anything. Lessig (2011) notes that virtually all provisions of US law that favor certain segments of society are set to expire after a modest number of years. These sunset provisions provide recurring opportunities for incumbent politicians to extort campaign contributions from those same segments to ensure the continuation of the favorable treatment.

The decline of 48 percent in otherTaxRegulations seems more curious for two additional reasons: First, it was preceded by a tripling of otherTaxRegulations between 1955 and 1965. Second, it was NOT accompanied by any comparable behavior of otherTaxCode. Instead, the latter grew each decade by between 17 and 53 percent, similar to but slower than the growth in IncomeTaxCode and IncomeTaxRegulations.

Accordingly, otherTaxRegulations for 1965 is replaced by the average of the numbers for 1955 and 1975, and EntireTaxRegulations for 1965 is comparably adjusted. This replaces (1322, 2960) for those two variables for 1965 with (565, 2203). In addition, otherTaxCodeAndRegs and EntireTaxCodeAndRegulations are also changed from (1626, 3507) to (870, 2751).

Independent of whether this adjustment is correct or not, it's clear that there have been roughly 3 words of regulations for each word in the tax code. Most of these are income tax regulations, which have recently contained 4.5 words for every word in code. The income tax code currently includes roughly 50 percent more words than other tax code.

Author(s)

Spencer Graves

Source

Tax Foundation: Number of Words in Internal Revenue Code and Federal Tax Regulations, 1955-2005 Scott Greenberg, "Federal Tax Laws and Regulations are Now Over 10 Million Words Long", October 08, 2015

References

J. Scott Moody, Wendy P. Warcholik, and Scott A. Hodge (2005) "The Rising Cost of Complying with the Federal Income Tax", The Tax Foundation Special Report No. 138.

Examples

data(UStaxWords)
plot(EntireTaxCodeAndRegs/1000 ~ year, UStaxWords, 
  type='b',
  ylab='Millions of words in US tax code & regs')

# Write to a file for Wikimedia Commons
## Not run: 
svg('UStaxWords.svg')

## End(Not run)
matplot(UStaxWords$year, UStaxWords[c(2:3, 5:6)]/1000,
    type='b', bty='n', ylab='',
    ylim=c(0, max(UStaxWords$EntireTaxCodeAndRegs)/1000),
    las=1, xlab="", cex.axis=2)
lines(EntireTaxCodeAndRegs/1000~year, UStaxWords, lwd=2)
## Not run: 
dev.off()

## End(Not run)
# lines 1:4 = IncomeTaxCode, otherTaxCode, 
#   IncomeTaxRegulations,
#   and otherTaxRegulations, respectively

##
## Plotting the original numbers 
##      without the adjustment
##
UStax. <- UStaxWords
UStax.[2,c(6:7, 9:10)] <- c(1322, 2960, 1626, 3507)
matplot(UStax.$year, UStax.[c(2:3, 5:6)]/1000,
      type='b', bty='n', ylab='',
      ylim=c(0, max(
          UStax.$EntireTaxCodeAndRegs)/1000),
      las=1, xlab="", cex.axis=2)
lines(EntireTaxCodeAndRegs/1000~year, UStax., 
        lwd=2)
# Note especially the anomalous behaviour of 
# line 4 = otherTaxRegulations.  As noted with
# "details" above, otherTaxRegulations could have
# tripled between 1955 and 1965, then fallen by 48
# percent between 1965 and 1975.  However, that
# does not seem credible, especially since there
# was no corresponding behavior in otherTaxCode.

##
## linear trend 
##
(newWdsPerYr <- lm(EntireTaxCodeAndRegs~year, 
    UStaxWords))
plot(UStaxWords$year, resid(newWdsPerYr))
# Roughly 150,000 additional words added each year
# since 1955.  
# No indication of nonlinearity.  
# adusted R-squared exceeds 99 percent.  

##
## linear trend with increased slope
## during the Reagan years
##
# linear spline with knots at
# 1981 and 1989 
Reagan <- pmax(0, pmin(
  (UStaxWords$year-1981)/8, 1))
plot(Reagan~year, UStaxWords, type='b')
UStaxWords$Reagan <- Reagan

ReaganMdl <- 
  EntireTaxCodeAndRegs~year + Reagan
fitReagan <- lm(ReaganMdl, UStaxWords )
summary(fitReagan)

Unemployment Duration

Description

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20

number of observations : 3343

Usage

data(UnempDur)

Format

A time series containing :

spell

length of spell in number of two-week intervals

censor1

= 1 if re-employed at full-time job

censor2

= 1 if re-employed at part-time job

censor3

1 if re-employed but left job: pt-ft status unknown

censor4

1 if still jobless

age

age

ui

= 1 if filed UI claim

reprate

eligible replacement rate

disrate

eligible disregard rate

logwage

log weekly earnings in lost job (1985$)

tenure

years tenure in lost job

Source

McCall, B.P. (1996) “Unemployment Insurance Rules, Joblessness, and Part-time Work”, Econometrica, 64, 647–682.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp. 603–8, 632–6, 658–62, 671–4 and 692.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Unemployment Duration

Description

a cross-section from 1993

number of observations : 452

observation : individuals

country : United States

Usage

data(Unemployment)

Format

A dataframe containing :

duration

duration of first spell of unemployment, t, in weeks

spell

1 if spell is complete

race

one of nonwhite, white

sex

one of male, female

reason

reason for unemployment, one of new (new entrant), lose (job loser), leave (job leaver), reentr (labor force reentrant)

search

'yes' if (1) the unemployment spell is completed between the first and second surveys and number of methods used to search > average number of methods used across all records in the sample, or, (2) for individuals who remain unemployed for consecutive surveys, if the number of methods used is strictly nondecreasing at all survey points, and is strictly increasing at least at one survey point

pubemp

'yes' if an individual used a public employment agency to search for work at any survey points relating to the individuals first unemployment spell

ftp1

1 if an individual is searching for full time work at survey 1

ftp2

1 if an individual is searching for full time work at survey 2

ftp3

1 if an individual is searching for full time work at survey 3

ftp4

1 if an individual is searching for full time work at survey 4

nobs

number of observations on the first spell of unemployment for the record

Source

Romeo, Charles J. (1999) “Conducting inference in semiparametric duration models under inequality restrictions on the shape of the hazard implied by the job search theory”, Journal of Applied Econometrics, 14(6), 587–605.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Provision of University Teaching and Research

Description

a cross-section from 1988

number of observations : 62

observation : schools

country : United Kingdom

Usage

data(University)

Format

A dataframe containing :

undstudents

undergraduate students

poststudents

postgraduate students

nassets

net assets

acnumbers

academic numbers

acrelnum

academic related numbers

clernum

clerical numbers

compop

computer operators

techn

technicians

stfees

student fees

acpay

academic pay

acrelpay

academic related pay

secrpay

secretarial pay

admpay

admin pay

agresrk

aggregate research rank

furneq

furniture and equipment

landbuild

land and buildings

resgr

research grants

Source

Glass, J.C., D.G. McKillop and N. Hyndman (1995) “Efficiency in the provision of university teaching and research : an empirical analysis of UK universities”, Journal of Applied Econometrics, 10(1), January–March, 61–72.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Medical Expenses in Vietnam (household Level)

Description

a cross-section from 1997

number of observations : 5999

observation : households

country : Vietnam

Usage

data(VietNamH)

Format

A dataframe containing :

sex

gender of household head (male,female)

age

age of household head

educyr

schooling year of household head

farm

farm household ?

urban

urban household ?

hhsize

household size

lntotal

log household total expenditure

lnmed

log household medical expenditure

lnrlfood

log household food expenditure

lnexp12m

log of total household health care expenditure for 12 months

commune

commune

Source

Vietnam World Bank Livings Standards Survey.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp.88–90.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Medical Expenses in Vietnam (individual Level)

Description

a cross-section from 1997

number of observations : 27765

observation : individuals

country : Vietnam

Usage

data(VietNamI)

Format

A dataframe containing :

pharvis

number of direct pharmacy visits

lnhhexp

log of total medical expenditure

age

age of household head

sex

gender (male,female)

married

married ?

educ

completed diploma level ?

illness

number of of illnesses experiences in past 12 months

injury

injured during survey period ?

illdays

number of illness days

actdays

number of days of limited activity

insurance

respondent has health insurance coverage ?

commune

commune

Source

Vietnam World Bank Livings Standards Survey.

References

Cameron, A.C. and P.K. Trivedi (2005) Microeconometrics : methods and applications, Cambridge, pp.848–853.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Panel Data of Individual Wages

Description

a panel of 595 observations from 1976 to 1982

number of observations : 4165

observation : individuals

country : United States

Usage

data(Wages)

Format

A dataframe containing :

exp

years of full-time work experience

wks

weeks worked

bluecol

blue collar ?

ind

works in a manufacturing industry ?

south

resides in the south ?

smsa

resides in a standard metropolitan statistical are ?

married

married ?

sex

a factor with levels (male,female)

union

individual's wage set by a union contract ?

ed

years of education

black

is the individual black ?

lwage

logarithm of wage

Source

Cornwell, C. and P. Rupert (1988) “Efficient estimation with panel data: an empirical comparison of instrumental variables estimators”, Journal of Applied Econometrics, 3, 149–155.

Panel study of income dynamics.

References

Baltagi, Badi H. (2003) Econometric analysis of panel data, John Wiley and sons, https://www.wiley.com/legacy/wileychi/baltagi/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wages, Experience and Schooling

Description

a panel of 595 observations from 1976 to 1982

number of observations : 3294

observation : individuals

country : United States

Usage

data(Wages1)

Format

A time series containing :

exper

experience in years

sex

a factor with levels (male,female)

school

years of schooling

wage

wage (in 1980 $) per hour

References

Verbeek, Marno (2004) A Guide to Modern Econometrics, John Wiley and Sons.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations,

Index.Time.Series

Wife Working Hours

Description

a cross-section from 1987

number of observations : 3382

observation : individuals

country : United States

Usage

data(Workinghours)

Format

A dataframe containing :

hours

wife working hours per year

income

the other household income in hundreds of dollars

age

age of the wife

education

education years of the wife

child5

number of children for ages 0 to 5

child13

number of children for ages 6 to 13

child17

number of children for ages 14 to 17

nonwhite

non–white ?

owned

is the home owned by the household ?

mortgage

is the home on mortgage ?

occupation

occupation of the husband, one of mp (manager or

unemp

local unemployment rate in %

Source

Lee, Myoung–Jae (1995) “Semi–parametric estimation of simultaneous equations with limited dependent variables : a case study of female labour supply”, Journal of Applied Econometrics, 10(2), April–June, 187–200.

References

Journal of Applied Econometrics data archive : http://qed.econ.queensu.ca/jae/.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Yen-dollar Exchange Rate

Description

weekly observations from 1975 to 1989

number of observations : 778

observation : country

country : Japan

Usage

data(Yen)

Format

A dataframe containing :

date

the date of the observation (19850104 is January, 4, 1985)

s

the ask price of the dollar in units of Yen in the spot market on Friday of the current week

f

the ask price of the dollar in units of Yen in the 30-day forward market on Friday of the current week

s30

the bid price of the dollar in units of Yen in the spot market on the delivery date on a current forward contract

Source

Bekaert, G. and R. Hodrick (1993) “On biases in the measurement of foreign exchange risk premiums”, Journal of International Money and Finance, 12, 115-138.

References

Hayashi, F. (2000) Econometrics, Princeton University Press, http://fhayashi.fc2web.com/, chapter 6, 438-443.

See Also

DM, Pound, Index.Source, Index.Economics, Index.Econometrics, Index.Observations, Index.Time.Series

Choice of Brand for Yogurts

Description

a cross-section

number of observations : 2412

observation : individuals

country : United States

Usage

data(Yogurt)

Format

A dataframe containing :

id

individuals identifiers

choice

one of yoplait, dannon, hiland, weight (weight watcher)

feat.z

is there a newspaper feature advertisement for brand z?

price.z

price of brand z

Source

Jain, Dipak C., Naufel J. Vilcassim and Pradeep K. Chintagunta (1994) “A random–coefficients logit brand–choice model applied to panel data”, Journal of Business and Economics Statistics, 12(3), 317.

References

Journal of Business Economics and Statistics web site : https://amstat.tandfonline.com/loi/ubes20.

See Also

Index.Source, Index.Economics, Index.Econometrics, Index.Observations

Countries in Banking Crises

Description

A data.frame identifying which of 70 countries had a banking crisis each year 1800:2010. The first column is year. The remaining columns carry the names of the countries; those columns are 1 for years with banking crises and 0 otherwise.

Usage

data(bankingCrises)

Format

A data.frame

Details

This file was created using the following command:

bankingCrises <- readFinancialCrisisFiles(FinancialCrisisFiles)

HOWEVER: This function was in Ecfun 0.2-3 but was removed in 0.2-4. It used gdata::read.xls, and gdata users were informed that gdata might be removed from CRAN, and any package that used it would also be removed. It seemed that the database that this function was designed to read may not have been updated, which suggested that it made sense to remove this function, because it there may not be any further need for it.

This dataset is an update of a subset of the data used to create Figure 10.1. Capital Mobility and the Incidence of Banking Crises, All Countries, 1800-2008, Reinhart and Rogoff (2009, p. 156).

The general upward trend visible in a plot of these data may be attributed to at least two different factors:

(1) The gradual increase in the proportion of human labor that is monetized.

(2) An increase in the general ability of cronies of those in power to gamble with other people's money in forming and bankrupting financial institutions. The marked feature of this plot is the virtual absence of banking crises during the period of the Bretton Woods agreement, 1944 to 1971. This period ended when US President Nixon in effect canceled the Bretton Woods agreement by taking the US off the silver standard.

Author(s)

Spencer Graves

Source

http://www.reinhartandrogoff.com

References

Carmen M. Reinhart and Kenneth S. Rogoff (2009) This Time Is Different: Eight Centuries of Financial Folly, Princeton U. Pr.

Examples

data(bankingCrises)
numberOfCrises <- rowSums(bankingCrises[-1], na.rm=TRUE)
plot(bankingCrises$year, numberOfCrises, type='b')

# Write to a file for Wikimedia Commons
## Not run: 
if(FALSE){
  svg('bankingCrises.svg')
  plot(bankingCrises$year, numberOfCrises, type='b', 
    cex.axis=2, las=1, xlab='', ylab='', bty='n', cex=0.5)
  abline(v=c(1945, 1971), lty='dashed', col='blue')
  text(1958, 14, 'Bretton Woods', srt=90, cex=2, col='blue')
  dev.off()
  }
  
## End(Not run)

Cyber Security Breaches

Description

data.frame of cyber security breaches involving health care records of 500 or more humans reported to the U.S. Department of Health and Human Services (HHS) as of June 27, 2014.

Usage

data(breaches)

Format

A data.frame with 1055 observations on the following 24 variables:

Number

integer record number in the HHS data base

Name_of_Covered_Entity

factor giving the name of the entity experiencing the breach

State

Factor giving the 2-letter code of the state where the breach occurred. This has 52 levels for the 50 states plus the District of Columbia (DC) and Puerto Rico (PR).

Business_Associate_Involved

Factor giving the name of a subcontractor (or blank) associated with the breach.

Individuals_Affected

integer number of humans whose records were compromised in the breach. This is 500 or greater; U.S. law requires reports of breaches involving 500 or more records but not of breaches involving fewer.

Date_of_Breach

character vector giving the date or date range of the breach. Recodes as Dates in breach_start and breach_end.

Type_of_Breach

factor with 29 levels giving the type of breach (e.g., "Theft" vs. "Unauthorized Access/Disclosure", etc.)

Location_of_Breached_Information

factor with 41 levels coding the location from which the breach occurred (e.g., "Paper", "Laptop", etc.)

Date_Posted_or_Updated

Date the information was posted to the HHS data base or last updated.

Summary

character vector of a summary of the incident.

breach_start

Date of the start of the incident = first date given in Date_of_Breach above.

breach_end

Date of the end of the incident or NA if only one date is given in Date_of_Breach above.

year

integer giving the year of the breach

Details

The data primarily consists of breaches that occurred from 2010 through early 2014 when the extract was taken. However, a few breaches are recorded including 1 from 1997, 8 from 2002-2007, 13 from 2008 and 56 from 2009. The numbers of breaches from 2010 - 2014 are 211, 229, 227, 254 and 56, respectively. (A chi-square test for equality of the counts from 2010 through 2013 is 4.11, which with 3 degrees of freedom has a significance probability of 0.25. Thus, even though the lowest number is the first and the largest count is the last, the apparent trend is not statistically significant under the usual assumption of independent Poisson trials.)

The following corrections were made to the file:

Number Name of Covered Entity Corrections
45 Wyoming Department of Health Cause of breach was missing. Added "Unauthorized
Access / Disclosure" per smartbrief.com/03/29/10
55 Reliant Rehabilitation Hospital North Cause of breach was missing. Added "Unauthorized
Houston Access / Disclosure" per Dissent. "Two Breaches
Involving Unauthorized Access Lead to Notification."
www.phiprivacy.net/two-breaches-involving-unauthorized-access-lead-to-notification; approximately 2010-04-20. This web page has since been removed, apparently without having been captured by archive.net.]
123 Aetna Cause of breach was missing. Added Improper
disposal per Aetna.com/news/newsReleases/2010/0630
157 Mayo Clinic Cause of breach was missing. Added Unauthorized
Access/Disclosure per Anderson, Howard. "Mayo Fires
"Employees in 2 Incidents: Both Involved
Unauthorized Access to Records."
Data Breach Today. N.p., 4 Oct. 2010
341 Saint Barnabas MedicL Center Misspelled "Saint Barnabas Medical Center"
347 Americar Health Medicare Misspelled "American Health Medicare"
484 Lake Granbury Medicl Ceter Misspelled "Lake Granbury Medical Center"
782 See list of Practices under Item 9 Replaced name as "Cogent Healthcare, Inc." checked
from XML and web documents
805 Dermatology Associates of Tallahassee Had 00/00/0000 on breach date. This was crossed
check to determine that it was Sept 4, 2013 with 916 records
815 Santa Clara Valley Medical Center Mistype breach year as 09/14/2913 corrected as 09/14/2013
961 Valley View Hosptial Association Misspelled "Valley View Hospital Association"
1034 Bio-Reference Laboratories, Inc. Date changed from 00/00/000 to 2/02/2014 as
subsequently determined.

Author(s)

Spencer Graves

Source

U.S. Department of Health and Human Services: Health Information Privacy: Breaches Affecting 500 or More Individuals

See Also

HHSCyberSecurityBreaches for a version of these data downloaded more recently. This newer version includes changes in reporting and in the variables included in the data.frame.

Examples

data(breaches)
quantile(breaches$Individuals_Affected)
# confirm that the smallest number is 500 
# -- and the largest is 4.9e6
# ... and there are no NAs

dDays <- with(breaches, breach_end - breach_start)
quantile(dDays, na.rm=TRUE)
# confirm that breach_end is NA or is later than 
# breach_start

Global cooling from a nuclear war

Description

Average surface temperature changes world wide and in the Northern Hemisphere 3 and 10 years after the injections of 5, 50 and 150 Tg (teragrams = millions of metric tons) of smoke into the upper troposphere, per Robock, Oman, and Stenchikov (2007).

These numbers are relative to the average for 1925-1975, which explains why the numbers are positive with smoke = 0.

Usage

data(coolingFromNuclearWar)

Format

A dataframe containing :

smoke

teragrams = millions of metric tons

dC3g, dC10g, dC3n, dC10n

average change in surface temperature 3 and 10 years after injection of smoke into the upper troposphere globally (g) or in the Northern Hemisphere (n) in degrees Celsius.

Source

Alan Robock, Luke Oman, and Georgiy L. Stenchikov (2007) Nuclear winter revisited with a modern climate model and current nuclear arsenals: Still catastrophic consequences, Journal of Geophysical Research, 112

Examples

data(coolingFromNuclearWar)
matplot(coolingFromNuclearWar[, 'smoke'], 
    coolingFromNuclearWar[, 2:5], type='l')
(linFit <- lm(cbind(dC3g, dC10g, dC3n, dC10n)~smoke, 
      coolingFromNuclearWar))
      
# total change 
dC <- as.matrix(coolingFromNuclearWar[, 2:5] - 
        rep(unlist(coolingFromNuclearWar[1, -1]), e=4))
(linFit0 <- lm(dC~smoke, coolingFromNuclearWar))
summary(linFit0)

Income Inequality in the US

Description

Data on quantiles of the distributions of family incomes in the United States. This combines three data sources:

(1) US Census Table F-1 for the central quantiles

(2) Piketty and Saez for the 95th and higher quantiles

(3) Gross Domestic Product and implicit price deflators from Measuring Worth. (NOTE: The Measuring Worth Web site, https://MeasuringWorth.com, often gives security warnings. The desired data still seems to be available and not corrupted, however.)

Usage

data(incomeInequality)

Format

A data.frame containing:

Year

numeric year 1947:2012

Number.thousands

number of families in the US

quintile1, quintile2, median, quintile3, quintile4, p95

quintile1, quintile2, quintile3, quintile4, and p95 are the indicated quantiles of the distribution of family income from US Census Table F-1. The media is computed as the geometric mean of quintile2 and quintile3. This is accurate to the extent that the lognormal distribution adequately approximates the central 20 percent of the income distribution, which it should for most practical purposes.

P90, P95, P99, P99.5, P99.9, P99.99

The indicated quantiles of family income per Piketty and Saez

realGDP.M, GDP.Deflator, PopulationK, realGDPperCap

real GDP in millions, GDP implicit price deflators, US population in thousands, and real GDP per capita, according to MeasuringWorth.com. (NOTE: The web address for this, https://MeasuringWorth.com, seems to be functional but may not be maintained to current internet security standards. It is therefore given here as text rather than a hot link.)

P95IRSvsCensus

ratio of the estimates of the 95th percentile of distributions of family income from the Piketty and Saez analysis of data from the Internal Revenue Service (IRS) and from the US Census Bureau.

The IRS has ranged between 72 and 98 percent of the Census Bureau figures for the 95th percentile of the distribution, with this ratio averaging around 75 percent since the late 1980s. However, this systematic bias is modest relative to the differences between the different quantiles of interest in this combined dataset.

personsPerFamily

average number of persons per family using the number of families from US Census Table F-1 and the population from MeasuringWorth. (Note: The web site for Measuring Worth, https://MeasuringWorth.com, often gives security warnings. It still seems to work. It seems that the web site is not maintained to current internet security standards.)

realGDPperFamily

personsPerFamily * realGDPperCap

mean.median

ratio of realGDPperFamily to the median. This is a measure of skewness and income inequality.

Details

For details on how this data.frame was created, see "F1.PikettySaez.R" in system.file('scripts', package='fda'). This provides links for files to download and R commands to read those files and convert them into an updated version of incomeInequality. This is a reasonable thing to do if it is more than 2 years since max(incomeInequality$year). All data are in constant 2012 dollars.

Author(s)

Spencer Graves

Source

United States Census Bureau, Table F-1. Income Limits for Each Fifth and Top 5 Percent of Families, All Races, https://www.census.gov/data/tables/time-series/demo/income-poverty/historical-income-inequality.html, accessed 2016-12-09.

Thomas Piketty and Emmanuel Saez (2003) "Income Inequality in the United States, 1913-1998", Quarterly Journal of Economics, 118(1) 1-39, https://eml.berkeley.edu/~saez/, update accessed February 28, 2014.

Louis Johnston and Samuel H. Williamson (2011) "What Was the U.S. GDP Then?" MeasuringWorth. (Note: Their web address, https://www.measuringworth.org/usgdp, often gives security warnings. The desired data still seems to be available there. However, it seems that the site is not maintained to current internet security standards. The data used in the current USGDPpresidents data set was extracted February 28, 2014.)

Examples

##
## Rato of IRS to census estimates for the 95th percentile
##
data(incomeInequality)
plot(P95IRSvsCensus~Year, incomeInequality, type='b')
# starts ~0.74, trends rapidly up to ~0.97,
# then drifts back to ~0.75
abline(h=0.75)
abline(v=1989)
# check
sum(is.na(incomeInequality$P95IRSvsCensus))
# The Census data runs to 2011;  Pikety and Saez runs to 2010.
quantile(incomeInequality$P95IRSvsCensus, na.rm=TRUE)
# 0.72 ... 0.98

##
## Persons per Family
##

plot(personsPerFamily~Year, incomeInequality, type='b')
quantile(incomeInequality$personsPerFamily)
# ranges from 3.72 to 4.01 with median 3.84
#  -- almost 4

##
## GDP per family
##
plot(realGDPperFamily~Year, incomeInequality, type='b', log='y')

##
## Plot the mean then the first quintile, then the median,
##            99th, 99.9th and 99.99th percentiles
##
plotCols <- c(21, 3, 5, 11, 13:14)
kcols <- length(plotCols)
plotColors <- c(1:6, 8:13)[1:kcols] # omit 7=yellow
plotLty <- 1:kcols

matplot(incomeInequality$Year, incomeInequality[plotCols]/1000,
        log='y', type='l', col=plotColors, lty=plotLty)

#*** Growth broadly shared 1947 - 1970, then began diverging
#*** The divergence has been most pronounced among the top 1%
#*** and especially the top 0.01%

##
## Growth rate by quantile 1947-1970 and 1970 - present
##
keyYears <- c(1947, 1970, 2010)
(iYears <- which(is.element(incomeInequality$Year, keyYears)))

(dYears <- diff(keyYears))
kk <- length(keyYears)
(lblYrs <- paste(keyYears[-kk], keyYears[-1], sep='-'))

(growth <- sapply(incomeInequality[iYears,], function(x, labels=lblYrs){
    dxi <- exp(diff(log(x)))
    names(dxi) <- labels
    dxi
} ))

# as percent
(gr <- round(100*(growth-1), 1))

# The average annual income (realGDPperFamily) doubled between
# 1970 and 2010 (increased by 101 percent), while the median household
# income increased only 23 percent.

##
## Income lost by each quantile 1970-2010
## relative to the broadly shared growth 1947-1970
##
(lostGrowth <- (growth[, 'realGDPperFamily']-growth[, plotCols]))
# 1947-1970:  The median gained 20% relative to the mean,
#           while the top 1% lost ground
# 1970-2010:  The median lost 79%, the 99th percentile lost 29%,
#           while the top 0.1% gained

(lostIncome <- (lostGrowth[2, ] *
                incomeInequality[iYears[2], plotCols]))
# The median family lost $39,000 per year in income
# relative to what they would have with the same economic growth
# broadly shared as during 1947-1970.
# That's slightly over $36,500 per year = $100 per day

(grYr <- growth^(1/dYears))
(grYr. <- round(100*(grYr-1), 1))

##
## Regression line:  linear spline
##

(varyg <- c(3:14, 21))
Varyg <- names(incomeInequality)[varyg]
str(F01ps <- reshape(incomeInequality[c(1, varyg)], idvar='Year',
                     ids=F1.PikettySeaz$Year,
                     times=Varyg, timevar='pctile',
                     varying=list(Varyg), direction='long'))
names(F01ps)[2:3] <- c('variable', 'value')
F01ps$variable <- factor(F01ps$variable)

# linear spline basis function with knot at 1970
F01ps$t1970p <- pmax(0, F01ps$Year-1970)

table(nas <- is.na(F01ps$value))
# 6 NAs, one each of the Piketty-Saez variables in 2011
F01i <- F01ps[!nas, ]

# formula:
# log(value/1000) ~ b*Year + (for each variable:
#     different intercept + (different slope after 1970))

Fit <- lm(log(value/1000)~Year+variable*t1970p, F01i)
anova(Fit)
# all highly significant
# The residuals may show problems with the model,
# but we will ignore those for now.

# Model predictions
str(Pred <- predict(Fit))

##
## Combined plot
##
#  Plot to a file?  Wikimedia Commons prefers svg format.
## Not run: 
if(FALSE){
  svg('incomeInequality8.svg')
#  If you want software to convert svg to another format 
#  such as png, consider GIMP (www.gimp.org).

#  Base plot

# Leave extra space on the right to label 
# with growth since 1970
  op <- par(mar=c(5, 4, 4, 5)+0.1)

  matplot(incomeInequality$Year, 
      incomeInequality[plotCols]/1000,
      log='y', type='l', col=plotColors, lty=plotLty,
      xlab='', ylab='', las=1, axes=FALSE, lwd=3)
  axis(1, at=seq(1950, 2010, 10),
     labels=c(1950, NA, 1970, NA, 1990, NA, 2010), 
     cex.axis=1.5)
  yat <- c(10, 50, 100, 500, 1000, 5000, 10000)
  axis(2, yat, labels=c('$10K', '$50K', '$100K', '$500K',
             '$1M', '$5M', '$10M'), las=1, cex.axis=1.2)

#  Label the lines
  pctls <- paste(c(20, 40, 50, 60, 80, 90, 95, 99, 
      99.5, 99.9, 99.99),
              '%', sep='')
  lineLbl0 <- c('Year', 'families K', pctls,
     'realGDP.M', 'GDP deflator', 'pop-K', 'realGDPperFamily',
     '95 pct(IRS / Census)', 'size of household',
     'average family income', 'mean/median')
  (lineLbls <- lineLbl0[plotCols])
  sel75 <- (incomeInequality$Year==1975)

  laby <- incomeInequality[sel75, plotCols]/1000

  text(1973.5, c(1.2, 1.2, 1.3, 1.5, 1.9)*laby[-1], 
    lineLbls[-1], cex=1.2)
  text(1973.5, 1.2*laby[1], lineLbls[1], cex=1.2, srt=10)

##
## Add lines + points for the knots in 1970
##
  End <- numeric(kcols)
  F01names <- names(incomeInequality)
  for(i in seq(length=kcols)){
    seli <- (as.character(F01i$variable) == 
        F01names[plotCols[i]])
#  with(F01i[seli, ], lines(Year, exp(Pred[seli]), 
#  col=plotColors[i]))
    yri <- F01i$Year[seli]
    predi <- exp(Pred[seli])
    lines(yri, predi, col=plotColors[i])
    End[i] <- predi[length(predi)]
    sel70i <- (yri==1970)
    points(yri[sel70i], predi[sel70i], 
        col=plotColors[i])
  }

##
##  label growth rates
##
  table(sel70. <- (incomeInequality$Year>1969))
  (lastYrs <- incomeInequality[sel70., 'Year'])
  (lastYr. <- max(lastYrs)+4)
#text(lastYr., End, gR., xpd=NA)
  text(lastYr., End, paste(gr[2, plotCols], '%', sep=''), 
    xpd=NA)
  text(lastYr.+7, End, paste(grYr.[2, plotCols], '%', 
    sep=''), xpd=NA)

##
##  Label the presidents
##
  abline(v=c(1953, 1961, 1969, 1977, 1981, 1989, 1993, 
    2001, 2009))
  (m99.95 <- with(incomeInequality, sqrt(P99.9*P99.99))/1000)

  text(1949, 5000, 'Truman')
  text(1956.8, 5000, 'Eisenhower', srt=90)
  text(1963, 5000, 'Kennedy', srt=90)
  text(1966.8, 5000, 'Johnson', srt=90)
  text(1971, 5*m99.95[24], 'Nixon', srt=90)
  text(1975, 5*m99.95[28], 'Ford', srt=90)
  text(1978.5, 5*m99.95[32], 'Carter', srt=90)
  text(1985.1, m99.95[38], 'Reagan' )
  text(1991, 0.94*m99.95[44], 'GHW Bush', srt=90)
  text(1997, m99.95[50], 'Clinton')
  text(2005, 1.1*m99.95[58], 'GW Bush', srt=90)
  text(2010, 1.2*m99.95[62], 'Obama', srt=90)
##
##  Done
##
  par(op) # reset margins

  dev.off() # for plot to a file
  }
  
## End(Not run)

Names with Character Set Problems

Description

A data.frame describing names containing character codes rare or non-existent in standard English text, e.g., with various accent marks that may not be coded consistently in different locales or by different software.

Usage

data(nonEnglishNames)

Format

A data.frame with two columns:

nonEnglish

a character vector containing names that often have non-standard characters with the non-standard characters replaced by "_"

English

a character vector containing a standard English-character translation of nonEnglish

See Also

grepNonStandardCharacters, subNonStandardCharacters

Examples

data(nonEnglishNames)


all.equal(ncol(nonEnglishNames), 2)

Nations with nuclear weapons

Description

Data on the 9 nuclear-weapon states as of April 2019.

Usage

data(nuclearWeaponStates)

Format

A dataframe containing :

nation

The name of the country (character). The former USSR is listed here as Russia.

ctry

ISO 31661- alpha-2 two-letter country codes (character).

firstTest

Date of first test of a nuclear weapon.

For Israel, which has not publicly acknowledged that it has nuclear weapons, this uses the Date of the Vela Incident.

firstTestYr

lubridate::decimal_date(firstTest)

yearsSinceLastFirstTest

c(NA, diff(firstTestYr))

nuclearWeapons

number of nuclear weapons

nYieldNA, nLowYield, nMidYield, nHighYield

number of weapons for which the yield in (nYieldNA) = unknown or variable, (nLowYield) = at most 15 kt (kilotons), the size of the Hiroshima bomb, (nMidYield) = greater than 15 but less that 50 kt, and (nHighYield) = at least 50 kt.

popM, popYr

popM = estimated population in millions for year popYr, per the Wikipedia article for the indicated country on 2020-02-05.

GDP_B, GDPyr

GDP_B = nominal Gross Domestic Product in billions of US dollars for year GDPyr, per the Wikipedia article for the indicated country on 2020-02-05.

Maddison

Country code used by the Maddison Project.

startNucPgm

Estimated date of the substantive commitment of the country to obtain nuclear weapons. See 'Details' below

startNucPgmYr

lubridate::decimal_date(startNucPgm)

Details

Most of the contents of this dataset are easily defined and not controversial. That's not true for the date upon which each country started its nuclear program, coded in startNucPgm and startNucPgmYr. The following summarizes the rationale behind the selection of the date for each country in this dataset.

US

The Manhattan Project started in stages. It was officially brought to the attention of the US government by a letter officially from Albert Einstein to US President Roosevelt, 1939-08-02. It was officially authorized 1942-01-19. We use this later date as the date of the start of the US nuclear-weapons program.

RU

Russian scientists were studying uranium before the first world war but didn't get much official attention until the atomic bombing of Hiroshima, 1945-08-06. Shortly thereafter on 1945-08-22, Stalin appointed Lavrentiy Beria. Beria was a able administrator and guided the project to fruition in four years.

GB

British scientists were among the leaders in nuclear technology in the late nineteenth century. They welcomed German-Jewish physicists Otto Frisch and Rudolf Peierls, who estimated in 1939 that only a few pounds or kilograms of uranium-235 might be enough to achieve a critical mass, whereas several tonnes of natural uranium would likely be required. Because of the war, this information was passed to scientists in the United States, who developed it into the bomb dropped on Hiroshima 1945-08-06, with help from British and Canadian scientists and Canadian industry. After the war, the US refused to share much of the information developed in the Manhattan Project with the British. British elites felt disrespected by US. On 1947-01-08, the British government decided to initiate their own nuclear-weapons program.

FR

France was one of the nuclear pioneers, going back to the work of Marie Curie and Henri Becquerel in the 1890s. In 1956 the French were deeply offended by the refusal of the US to support them in the Suez Crisis. On France and Israel secretly agreed to collaborate in the development of nuclear weapons.

CN

Mao Zedong reportedly decided to begin a Chinese nuclear-weapons program during the First Taiwan Strait Crisis of 1954–1955. That crisis was resolved shortly after 1955-04-23, when China stated it was willing to negotiate. We use this as the date of the start of China's nuclear weapons program.

IN

Indian scientists started research on nuclear weapons before Indian independence but didn't make a substantive commitment to actually making a nuclear weapon until they lost territory to China in the Sino-Indian War that ended 1962-11-21. We use that date as the date for the initiation of India's nuclear-weapons program.

IL

Israel's first Prime Minister David Ben-Gurion was reportedly "nearly obsessed" with obtaining nuclear weapons to prevent the Holocaust from recurring. For present purposes, we use 1949-03-10, the date of the end of the 1948 Arab–Israeli War, as the beginning of Israel's nuclear-weapons program.

PK

Pakistan's elite were totally humiliated by their defeat in the Indo-Pakistani War of 1971, 1971-12-03 / -16: That war ended the Bangladesh Liberation War, by which Pakistan lost over half their population and 14 percent of their land area. Prime Minister Zulfiqar Ali Bhutto compared Pakistan's surrender to the Treaty of Versailles, which Germany was forced to sign in 1919. Bhutto observed 1972-01-20 that a Pakistani scientist had been part of the Manhattan Project, and Pakistani scientists could do the same in Pakistan. While significant funding seemed not to have come until later, 1972-01-20 is the date we will use here for the beginning of Pakistan's nuclear-weapons program.

KP

The 1950-1953 Korean War ended with a cease-fire, not an official end to hostilities. Since then North Korea has perceived nuclear threats from the US. In 1956 the Soviet Union began giving North Korean scientists and engineers "basic knowledge" to help them initiate a nuclear program. About 1962, North Korea committed itself to what it called "all-fortressization", which was the beginning of the hyper-militarized North Korea of today. North Korea reportedly asked the Soviet Union for help with a nuclear weapons program in 1963 and was turned down. China turned down similar requests in 1964 and 1974. Around 1980 North Korea began mining its own supplies of uranium and building its own factory to produce yellowcake. (See also Bolton, 2012.) For lack of something better, we use 1980-01-01 as the start of North Korea's nuclear weapons program. They clearly wanted nuclear weapons much earlier but didn't seem to move seriously in the direction of developing nuclear weapons until around

Source

Overview from World Nuclear Weapon Stockpile

firstTest from Wikipedia, "List of states with nuclear weapons"

US from Hans M. Kristensen & Robert S. Norris (2018) United States nuclear forces,2018, Bulletin of the Atomic Scientists, 74:2, 120-131, doi:10.1080/00963402.2018.1438219

Russia from Hans M. Kristensen & Matt Korda (2019) Russian nuclear forces, 2019, Bulletin of the Atomic Scientists, 75:2, 73-84, doi:10.1080/00963402.2019.1580891

UK from Robert S. Norris and Hans M. Kristensen (2013) The British nuclear stockpile, 1953-2013, Bulletin of the Atomic Scientists, 69:4, 69-75s, doi:10.1177/0096340213493260

France from Robert S. Norris & Hans M. Kristensen (2008) French nuclear forces, 2008, Bulletin of the Atomic Scientists, 64:4, 52-54, 57, doi:10.2968/064004012

China from Hans M. Kristensen & Robert S. Norris (2018) Chinese nuclear forces, 2018,Bulletin of the Atomic Scientists, 74:4, 289-295, doi:10.1080/00963402.2018.1486620

India from Hans M. Kristensen & Robert S. Norris (2017) Indian nuclear forces, 2017,Bulletin of the Atomic Scientists, 73:4, 205-209, doi:10.1080/00963402.2017.1337998

Israel from Hans M. Kristensen and Robert S. Norris (2014) Israeli nuclear weapons, 2014, Bulletin of the Atomic Scientists, 70:6, 97-115, doi:10.1177/0096340214555409

Pakistan from Hans M. Kristensen, Robert S. Norris & Julia Diamond (2018)Pakistani nuclear forces, 2018, Bulletin of the Atomic Scientists, 74:5, 348-358, doi:10.1080/00963402.2018.1507796

North Korea from Hans M. Kristensen & Robert S. Norris (2018) North Korean nuclear capabilities, 2018, Bulletin of the Atomic Scientists, 74:1, 41-51, doi:10.1080/00963402.2017.1413062

Derek Bolton (2012) North Korea's Nuclear Program (2012-08, American Security Program, accessed 2020-07-15) https://www.americansecurityproject.org/ASP%20Reports/Ref%200072%20-%20North%20Korea%E2%80%99s%20Nuclear%20Program%20.pdf

Examples

data(nuclearWeaponStates)
plot(yearsSinceLastFirstTest~firstTest, 
    nuclearWeaponStates, type='h', xlab='', ylab='')
with(nuclearWeaponStates, 
  text(firstTest, yearsSinceLastFirstTest, ctry))

Political knowledge in the US and Europe

Description

Data from McChesney and Nichols (2010) on domestic and international knowledge in Denmark, Finland, the UK and the US among college graduates, people with some college, and roughly 12th grade only.

Usage

data(politicalKnowledge)

Format

A data.frame containing 12 columns and 4 rows.

country

a character vector of Denmark, Finland, UK, and US, being the four countries compared in this data set.

DomesticKnowledge.hs, DomesticKnowledge.sc, DomesticKnowledge.c

percent correct answers to calibrated questions regarding knowledge of prominent items in domestic news in a survey of residents of the four countries among college graduates (ending ".c"), some college (".sc") and high school (".hs"). Source: McChesney and Nichols (2010, chapter 1, chart 8).

InternationalKnowledge.hs, InternationalKnowledge.sc, InternationalKnowledge.c

percent correct answers to calibrated questions regarding knowledge of prominent items in international news in a survey of residents of the four countries by education level as for DomesticKnowledge. Source: McChesney and Nichols (2010, chapter 1, chart 7).

PoliticalKnowledge.hs, PoliticalKnowledge.sc, PoliticalKnowledge.c

average of domestic and international knowledge

PublicMediaPerCapita

Per capital spending on public media in 2007 in US dollars from McChesney and Nichols (2010, chapter 4, chart 1)

PublicMediaRel2US

Spending on public media relative to the US, being PublicMediaPerCapita / PublicMediaPerCapita[4].

Author(s)

Spencer Graves

Source

Robert W. McChesney and John Nichols (2010) The Death and Life of American Journalism (Nation Books)

Examples

##
## 1. Combine first 2 rows 
##
data(politicalKnowledge)
pk <- politicalKnowledge[-1,]
pk[1, -1] <- ((politicalKnowledge[1, -1] + 
                 politicalKnowledge[2, -1])/2)
pk[1, 'country'] <- 'DK-FI'

##
## 2.  plot
##
xlim <- range(pk[, 'PublicMediaPerCapita'])
ylim <- 100*range(pk[2:7])
text.cex <- 2

# to label the lines 
(US.UK <- (pk[2, -1]+pk[3, -1])/2)

#png('Knowledge v. public media.png')
op <- par(mar=c(5, 7, 4, 2)+.1)
plot(c(0, 110), 100*ylim, type='n', axes=FALSE,
     xlab='public media $ per capita',
     ylab='Political Knowledge\n(% of standard questions)',
     cex.lab=2)
axis(1, cex.axis=2)
axis(2, las=2, cex.axis=2)
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.hs,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.sc,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.c,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.hs,
               type='b', pch=' '))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.sc,
               type='b', pch=' '))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.c,
               type='b', pch=' '))
with(US.UK, text(PublicMediaPerCapita, 100*PoliticalKnowledge.hs,
                 'High School\nor less', srt=37, cex=1.5))
with(US.UK, text(PublicMediaPerCapita, 100*PoliticalKnowledge.sc,
                 'some\ncollege', srt=10.5, cex=1.5))
with(US.UK, text(PublicMediaPerCapita, 100*PoliticalKnowledge.c,
                 "Bachelor's\nor more", srt=-1, cex=1.5))

par(op)
#dev.off()

##
## redo for Wikimedia commons
## without English axis labels 
## to facilitate multilingual use 
##
#svg('Knowledge v. public media.svg')
op <- par(mar=c(3,3,2,2)+.1)
plot(c(0, 110), 100*ylim, type='n', axes=FALSE,
     xlab='', ylab='', cex.lab=2)
axis(1, cex.axis=2)
axis(2, las=2, cex.axis=2)
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.hs,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.sc,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, text(PublicMediaPerCapita, 100*PoliticalKnowledge.c,
              country, cex=text.cex, xpd=NA, 
              col=c('forestgreen', 'orange', 'red')))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.hs,
               type='b', pch=' '))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.sc,
               type='b', pch=' '))
with(pk, lines(PublicMediaPerCapita, 100*PoliticalKnowledge.c,
               type='b', pch=' '))
par(op)
#dev.off()

Global Terrorism Database yearly summaries

Description

The Global Terrorism Database (GTD) "is a database of incidents of terrorism from 1970 onward". Through 2020, this database contains information on 209,706 incidents.

terrorism provides a few summary statistics along with an ordered factor methodology, which Pape et al. insisted is necessary, because an increase of over 70 percent in suicide terrorism between 2007 and 2013 is best explained by a methodology change in GTD that occurred on 2011-11-01; Pape's own Suicide Attack Database showed a 19 percent decrease over the same period.

Usage

  data(terrorism)
  data(incidents.byCountryYr)
  data(nkill.byCountryYr)

Format

incidents.byCountryYr and nkill.byCountryYr are matrices giving the numbers of incidents and numbers of deaths by year and by location of the event for 204 countries (rows) and for all years between 1970 and 2060 (columns) except for 1993, for which the entries are all NA, because the raw data previously collected was lost (though the total for that year is available in the data.frame terrorism).

NOTES:

1. For nkill.byCountryYr and for terrorism[c('nkill', 'nkill.us')], NAs in GTD were treated as 0. Thus the actual number of deaths were likely higher, unless this was more than offset by incidents being classified as terrorism, when they should not have been.

2. incidents.byCountryYr and nkill.byCountryYr are NA for 1993, because the GTD data for that year were lost.

terrorism is a data.frame containing the following:

year

integer year, 1970:2020.

methodology

an ordered factor giving the methodology / organization responsible for the data collection for most of the given year. The Pinkerton Global Intelligence Service (PGIS) managed data collection from 1970-01-01 to 1997-12-31. The Center for Terrorism and Intelligence Studies (CETIS) managed the project from 1998-01-01 to 2008-03-31. The Institute for the Study of Violent Groups (ISVG) carried the project from 2008-04-01 to 2011-10-31. The National Consortium for the Study of Terrorism and Responses to Terrorism (START) has managed data collection since 2011-11-01. For this variable, partial years are ignored, so methodology = CEDIS for 1998:2007, ISVG for 2008:2011, and START for more recent data.

method

a character vector consisting of the first character of the levels of methodology:

c('p', 'c', 'i', 's')

incidents

integer number of incidents identified each year.

NOTE: sum(terrorism[["incidents"]]) = 214660 = 209706 in the GTD database plus 4954 for 1993, for which the incident-level data were lost.

incidents.us

integer number of incidents identified each year with country_txt = "United States".

suicide

integer number of incidents classified as "suicide" by GTD variable suicide = 1. For 2007, this is 359, the number reported by Pape et al. For 2013, it is 624, which is 5 more than the 619 mentioned by Pape et al. Without checking with the SMART project administrators, one might suspect that 5 more suicide incidents from 2013 were found after the data Pape et al. analyzed but before the data used for this analysis.

suicide.us

Number of suicide incidents by year with country_txt = "United States".

nkill

number of confirmed fatalities for incidents in the given year, including attackers = sum(nkill, na.rm=TRUE) in the GTD incident data.

NOTE: nkill in the GTD incident data includes both perpetrators and victims when both are available. It includes one when only one is available and is NA when neither is available. However, in most cases, we might expect that the more spectacular and lethal incidents would likely be more accurately reported. To the extent that this is true, it means that when numbers are missing, they are usually zero or small. This further suggests that the summary numbers recorded here probably represent a slight but not substantive undercount.

nkill.us

number of U.S. citizens who died as a result of incidents for that year = sum(nkill.us, na.rm=TRUE) in the GTD incident data.

NOTES:

1. This is subject to the same likely modest undercount discussed with nkill.)

2. These are U.S. citizens killed regardless of location. This explains at least part of the discrepancies between terrorism[, 'nkill.us'] and nkill.byCountryYr['United States', ].

nwound

number of people wounded. (This is subject to the same likely modest undercount discussed with nkill.)

nwound.us

Number of U.S. citizens wounded in terrorist incidents for that year = sum(nwound.us, na.rm=TRUE) in the GTD incident data. (This is subject to the same likely modest undercount discussed with nkill.)

pNA.nkill, pNA.nkill.us, pNA.nwound, pNA.nwound.us

proportion of observations by year with missing values. These numbers are higher for the early data than more recent numbers. This is particularly true for nkill.us and nwound.us, which exceed 90 percent for most of the period with methodology = PGIS, prior to 1998.

worldPopulation, USpopulation

Estimated de facto population in thousands living in the world and in the US as of 1 July of the year indicated, according to the Population Division of the Department of Economic and Social Affairs of the United Nations; see "Sources" below.

worldDeathRate, USdeathRate

Crude death rate (deaths per 1,000 population) worldwide and in the US, according to the World Bank; see "Sources" below. This World Bank data set includes USdeathRate for each year from 1900 to 2020.

NOTE: USdeathRate to 2009 is to two significant digits only. Other death rates carry more significant digits.

worldDeaths, USdeaths

number of deaths by year in the world and US

worldDeaths = worldPopulation * worldDeathRate.

USdeaths were computed by summing across age groups in "Deaths_5x1.txt" for the United States, downloaded from https://www.mortality.org/Country/Country?cntr=USA from the Human Mortality Database; see sources below.

kill.pmp, kill.pmp.us

terrorism deaths per million population worldwide and in the US =

nkill / (0.001*worldPopulation)

nkill.us / (0.001*USpopulation)

pkill, pkill.us

terrorism deaths as a proportion of total deaths worldwide and in the US

pkill = nkill / worldDeaths

pkill.us = nkill.us / USdeaths

Details

As noted with the "description" above, Pape et al. noted that the GTD reported an increase in suicide terrorism of over 70 percent between 2007 and 2013, while their Suicide Attack Database showed a 19 percent decrease over the same period. Pape et al. insisted that the most likely explanation for this difference is the change in the organization responsible for managing that data collection from ISVG to START.

If the issue is restricted to how incidents are classified as "suicide terrorism", this concern does not affect the other variables in this summary.

However, if it also impacts what incidents are classified as "terrorism", it suggests larger problems.

Author(s)

Spencer Graves

Source

START (National Consortium for the Study of Terrorism and Responses to Terrorism). (2022). Global Terrorism Database, 1970 - 2020 [data file]. Retrieved from https://www.start.umd.edu/gtd, 2024-10-17.

See also the Global Terrorism Database maintained by the National Consortium for the Study of Terrorism and Responses to Terrorism (START, 2022), https://www.start.umd.edu/gtd.

The world and US population figures came from "Total Population - Both Sexes", World Population Prospects 2022, published by the Population Division, World Population Prospects, of the United Nations, accessed 2022-10-09.

Human Mortality Database. University of California, Berkeley (USA), and Max Planck Institute for Demographic Research (Germany), accessed 2022-10-11.

References

Robert Pape, Keven Ruby, Vincent Bauer and Gentry Jenkins, "How to fix the flaws in the Global Terrorism Database and why it matters", The Washington Post, August 11, 2014 (accessed 2016-01-09).

Examples

data(terrorism)
##
## plot deaths per million population 
##
plot(kill.pmp~year, terrorism, 
     pch=method, type='b')
plot(kill.pmp.us~year, terrorism, 
     pch=method, type='b', 
     log='y', las=1)
     
# terrorism as parts per 10,000 
# of all deaths 

plot(pkill*1e4~year, terrorism, 
     pch=method, type='b', 
     las=1)
plot(pkill.us*1e4~year, terrorism, 
     pch=method, type='b', 
     log='y', las=1)
     
# plot number of incidents, number killed, 
# and proportion NA

plot(incidents~year, terrorism, type='b', 
      pch=method)

plot(nkill.us~year, terrorism, type='b', 
      pch=method)
plot(nkill.us~year, terrorism, type='b', 
      pch=method, log='y')

plot(pNA.nkill.us~year, terrorism, type='b', 
      pch=method)
abline(v=1997.5, lty='dotted', col='red')

##
## by country by year
##
data(incidents.byCountryYr)
data(nkill.byCountryYr)

yr <- as.integer(colnames(
  incidents.byCountryYr))
str(maxDeaths <- apply(nkill.byCountryYr, 
                       1, max) )
str(omax <- order(maxDeaths, decreasing=TRUE))
head(maxDeaths[omax], 8)
tolower(substring( 
  names(maxDeaths[omax[1:8]]), 1, 2))
pch. <- c('i', 'g', 'f', 'l', 
          's', 'c', 'u', 'p')
cols <- 1:4

matplot(yr, sqrt(t(
  nkill.byCountryYr[omax[1:8], ])),
  type='b', pch=pch., axes=FALSE, 
  ylab='(square root scale)   ', xlab='', 
  col=cols,
  main='number of terrorism deaths\nby country') 
axis(1)
(max.nk <- max(nkill.byCountryYr[omax[1:8], ]))
i.nk <- c(1, 100, 1000, 3000, 
          5000, 7000, 10000)
cbind(i.nk, sqrt(i.nk))
axis(2, sqrt(i.nk), i.nk, las=1)
ip <- paste(pch., names(maxDeaths[omax[1:8]]))
legend('topleft', ip, cex=.55, 
       col=cols, text.col=cols)