Using the P90/P10 index to measure U.S. inequality trends with current population survey data: a view from inside the census bureau vaults

TLDR: In this article, the authors show that using P90/P10 does not completely obviate time-inconsistency problems, especially for household income inequality trends, when used with public use data.

Abstract: The March Current Population Survey (CPS) is the primary data source for estimation of levels and trends in labor earnings and income inequality in the USA. Time-inconsistency problems related to top coding in theses data have led many researchers to use the ratio of the 90th and 10th percentiles of these distributions (P90/P10) rather than a more traditional summary measure of inequality. With access to public use and restricted-access internal CPS data, and bounding methods, we show that using P90/P10 does not completely obviate time-inconsistency problems, especially for household income inequality trends. Using internal data, we create consistent cell mean values for all top-coded public use values that, when used with public use data, closely track inequality trends in labor earnings and household income using internal data. But estimates of longer-term inequality trends with these corrected data based on P90/P10 differ from those based on the Gini coefficient. The choice of inequality measure matters.

Figures

Table 1. Income Items Reported in the Current Population Survey

Figure 6. Trends in Consistently Top Coded Gini Coefficient and Cell-mean adjusted P90/P10 Estimates for the Size-adjusted Household Income of Individuals

Table 4. P90/P10 Estimates for the Size-adjusted Household Income of Individuals

Table 2. P90/P10 Estimates for Wages and Salaries of Full-time Full-year Workers

Figure 1. P90/P10 Estimates for Size-Adjusted Household Income of Individuals, by Year

Figure 2. Percentage of Individuals with Size-Adjusted Household Income Censored in the Public Use CPS File

Full text

Discussion Papers
Using the P90/P10 Index to Measure
US Inequality Trends with Current Population
Survey Data: A View from Inside the Census Bureau Vaults
Richard V. Burkhauser
Shuaizhang Feng
Stephen P. Jenkins
Berlin, June 2007

Opinions expressed in this paper are those of the author and do not necessarily reflect
views of the institute.
IMPRESSUM
© DIW Berlin, 2007
DIW Berlin
German Institute for Economic Research
Königin-Luise-Str. 5
14195 Berlin
Tel. +49 (30) 897 89-0
Fax +49 (30) 897 89-200
http://www.diw.de
ISSN print edition 1433-0210
ISSN electronic edition 1619-4535
Available for free downloading from the DIW Berlin website.

Discussion Papers 699
Richard V. Burkhauser*
Shuaizhang Feng**
Stephen P. Jenkins***
Using the P90/P10 Index to Measure US Inequality Trends
with Current Population Survey Data: A View from Inside
the Census Bureau Vaults
Berlin, June 2007
* Cornell University, Dept. of Policy Analysis and Management, and DIW Berlin; rvb1@cornell.edu
** Shanghai University of Finance and Economics
*** University of Essex, ISER, and DIW Berlin; stephenj@essex.ac.uk

Abstract
The March Current Population Survey (CPS) is the primary data source for estimation of
levels and trends in labor earnings and income inequality in the USA. Time-inconsistency
problems related to top coding in theses data have led many researchers to use the ratio of the
90th and 10th percentiles of these distributions (P90/P10) rather than a more traditional sum-
mary measure of inequality. With access to public use and restricted-access internal CPS data,
and bounding methods, we show that using P90/P10 does not completely obviate time-
inconsistency problems, especially for household income inequality trends. Using internal
data, we create consistent cell mean values for all top-coded public use values that, when used
with public use data, closely track inequality trends in labor earnings and household income
using internal data. But estimates of longer-term inequality trends with these corrected data
based on P90/P10 differ from those based on the Gini coefficient. The choice of inequality
measure matters.
JEL codes: D3; J3; C8
Key words: inequality, income, earnings, Current Population Survey, decile ratio, Gini coeffi-
cient

Discussion Papers 699
Contents
Contents
1 Introduction .........................................................................................................................1
2 Censoring problems in the Current Population Survey .................................................. 4
3 Bounds for P90/P10 and Seven Series of Estimates .........................................................7
3.1 Bounds on estimates of P90/P10 from top coded data .................................................. 7
3.2 Seven Series of P90/P10 Estimates................................................................................ 9
4 Trends in wages and labor earnings inequality for full-time, full-year, workers........11
5 Trends in size-adjusted household income inequality for individuals..........................15
6 Longer-term trends in inequality using Adjusted public use CPS data: .....................20
7 Summary and Conclusions...............................................................................................25
I