Get access

USING THE P90/P10 INDEX TO MEASURE U.S. INEQUALITY TRENDS WITH CURRENT POPULATION SURVEY DATA: A VIEW FROM INSIDE THE CENSUS BUREAU VAULTS

Authors


  • Note: The research in this paper was conducted while the first two authors were Special Sworn Status researchers of the U.S. Census Bureau at the New York Census Research Data Center at Cornell University. Research results and conclusions expressed are those of the authors and do not necessarily reflect the views of the U.S. Census Bureau. This paper has been screened to ensure that no confidential data are disclosed. Support for this research from the National Science Foundation (award nos. SES-0427889 SES-0322902, and SES-0339191) and the National Institute for Disability and Rehabilitation Research (H133B040013 and H133B031111) is gratefully acknowledged. Jenkins' research was supported by core funding from the University of Essex and the U.K. Economic and Social Research Council for the Research Centre on Micro-Social Change and the United Kingdom Longitudinal Studies Centre. We thank Jeff Larrimore, Ludmila Rovba and Mathis Schroeder for their research assistance on this project and for their comments on earlier versions of this paper, and Pinky Chandra and Lisa Marie Dragoset, the Cornell Census RDC Administrators, and all their Bureau of Census colleagues who have helped this project along, especially Edward J. Welniak, Jr. and Brian P. Holly.

*Richard V. Burkhauser, Sarah Gibson Blanding Professor, Cornell University, Policy Analysis and Management, 125 MVR Hall, Ithaca, New York 14853-4401, USA (rvb1@cornell.edu).

Abstract

The March Current Population Survey (CPS) is the primary data source for estimation of levels and trends in U.S. earnings and income inequality. However, time-inconsistency problems related to top coding lead many CPS users to measure inequality via the ratio of the 90th to the 10th percentile (P90/P10) rather than by more traditional summary measures. With access to public use and restricted-access internal CPS data, and by applying bounding methods, we show that using P90/P10 does not completely obviate time-inconsistency problems, especially in capturing 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 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 still matters.

Get access to the full text of this article

Ancillary