Publications on Income Inequality
Economics Letters
Extended Working Paper Version (NBER Working Paper w14458)
Research Poster presented at SOLE, 2009
Abstract: Using the Census Bureau’s internal March Current Population Surveys (CPS) file, we construct and make available
variances and cell means for all topcoded income values in the public-use version of these data.
We then provide a procedure that allows researchers with access only to the public-use March CPS data
to take advantage of this added information when imputing its topcoded income values. As an example of
its value we show how our new procedure improves on existing imputation methods in the labor earnings
inequality literature.
Monthly Labor Review 132 (August 2009), 3-18
download paper as a PDF (via. Bureau of Labor Statistics website)
Abstract: Most empirical studies of trends in labor earnings gaps by gender, race or education level are based
on data from the public use March Current Population Survey (CPS). Using the internal March CPS, we
show that inconsistent topcoding in the public use data will understate these gaps and inaccurately
capture their trends. We create a cell mean series beginning in 1975 that provides the mean of all
values above the topcode for each income source in the public use March CPS and better approximate
earnings gaps found in the internal March CPS than was previously possible using publically available
data.
U.S. Census Bureau, 2008 Research Report: Center for Economic Studies
and Research Data Centers (Chapter 4), Washington, DC: GPO (2009)
Download full research report as a PDF (via. U.S. Census Bureau CES website)
Abstract: The March Current Population Survey (CPS) is the primary data source used by public policy
researchers and administrators to investigate trends in U.S. income and its distribution. For
con?dentiality reasons, the U.S. Census Bureau topcodes each of the 24 sources of income (11
income sources prior to 1988) in the public-use CPS. However, this topcoding — the suppression
of income values above some level in the public-use CPS data for confidentiality reasons -
has not been consistent over time. Below we discuss a new set of papers that offer a solution
to this problem using a series of created values, which, when used together with the
public-use CPS data, will closely approximate income and inequality levels and their trends
based on the internal CPS.
Journal of Economic and Social Measurement 33 (2008), 89-128
download paper as a PDF*
Abstract: Using the internal March CPS, we create and in this paper distribute to the larger
research community a cell mean series that provides the mean of all income values
above the topcode for any income source of any individual in the public use March CPS
that has been topcoded since 1976. We also describe our construction of this series.
When we use this series together with the public use March CPS, we closely match the
yearly mean income levels and income inequalities of the U.S. population found using
the internal March CPS data.
Working Papers on Income Inequality
(Job Market Paper)
Working Paper
Abstract: While much of the research on the rise in inequality in the United
States since the 1960s has focused on labor earnings inequality, there is little evidence regarding how closely these
labor earnings inequality trends correlate to broader measures of income inequality. This paper first compares male
and female labor earnings inequality to that of household income. It then uses a shift-share analysis
to analyze the change in income inequality accunted for by changes in male and female earnings
distributions and changing household characteristics. In doing so, it is evident that the factors
contributing to the rapid rise in household income inequality in the 1970s and 1980s differ
substantially from those contributing to the slower increase in the 1990s. In contrast to findings for
the 1970s and 1980s, in more recent years increases in male earnings inequality largely account for
the changes in household income inequality while assortative mating and changes in the correlation
between male and female earnings have mitigated household income inequality growth.
NBER Working Paper w15320
Abstract: Although the vast majority of US research on trends in the inequality of family income is based on public-use March
Current Population Survey (CPS) data, a new wave of research based on Internal Revenue Service (IRS) tax return data
reports substantially higher levels of inequality and faster growing trends. We show that these apparently inconsistent
estimates can largely be reconciled once one uses internal CPS data (which better captures the top of the income
distribution than public-use CPS data) and defines the income distribution in the same way. Using internal CPS data for
1967–2006, we closely match the IRS data-based estimates of top income shares reported by Piketty and Saez (2003), with
the exception of the share of the top 1 percent of the distribution during 1993–2000. Our results imply that, if inequality
has increased substantially since 1993, the increase is confined to income changes for those in the top 1 percent of the distribution.
NBER Working Paper w14247
Abstract: Using internal and public use March Current Population Survey (CPS) data, we analyze trends in US
income inequality (1975-2004). We find that the upward trend in income inequality prior to 1993
significantly slowed thereafter once we control for top coding in the public use data and censoring
in the internal data. Because both series do not capture trends at the very top of the income
distribution, we use a multiple imputation approach in which values for censored observations are
imputed using draws from a Generalized Beta distribution of the Second Kind (GB2) fitted to internal
data. Doing so, we find income inequality trends similar to those derived from unadjusted internal
data. Our trend results are generally robust to the choice of inequality index, whether Gini
coefficient or other commonly-used indices.
CES Working Paper CES-WP-09-05
Abstract: To measure income inequality with right censored (topcoded) data, we propose multiple imputation
for censored observations using draws from Generalized Beta of the Second Kind distributions to
provide partially synthetic datasets analyzed using complete data methods. Estimation and inference
uses Reiter’s (Survey Methodology 2003) formulae. Using Current Population Survey (CPS) internal
data, we find few statistically significant differences in income inequality for pairs of years
between 1995 and 2004. We also show that using CPS public use data with cell mean imputations
may lead to incorrect inferences about inequality differences. Multiply-imputed public use data
provide an intermediate solution.
Contact Information
Jeff Larrimore
Department of Economics
404 Uris Hall
Cornell University
Ithaca, NY 14853
E-mail: jhl42@cornell.edu