Match Bias in Wage Gap Estimates Due to Earnings Imputation

39 Pages Posted: 10 Jun 2003

See all articles by Barry T. Hirsch

Barry T. Hirsch

Georgia State University; IZA Institute of Labor Economics

Edward J. Schumacher

Trinity University - Department of Health Care Administration

Date Written: May 2003

Abstract

About 30% of workers in the CPS have earnings imputed. Wage gap estimates are biased toward zero when the attribute being studied (e.g., union status) is not a criterion used to match donors to nonrespondents. An expression for "match bias" is derived in which attenuation equals the sum of match error rates. In practice, attenuation can be approximated by the proportion with imputed earnings. Union wage gap estimates with match bias removed are presented for 1973-2001. Estimates in recent years are biased downward 5 percentage points. Bias in gap estimates accompanying other non-match criteria (public sector, industry, etc.) is examined.

Keywords: Wage Differentials, Hot Deck Imputation, Match Bias, CPS, Union Wage Premiums

JEL Classification: J3, J5, C81

Suggested Citation

Hirsch, Barry T. and Schumacher, Edward J., Match Bias in Wage Gap Estimates Due to Earnings Imputation (May 2003). IZA Discussion Paper No. 783. Available at SSRN: https://ssrn.com/abstract=282918

Barry T. Hirsch (Contact Author)

Georgia State University ( email )

Department of Economics
Andrew Young School of Policy Studies
Atlanta, GA 30302-3992
United States
404-413-0880 (Phone)
404-413-0145 (Fax)

HOME PAGE: http://www2.gsu.edu/bhirsch

IZA Institute of Labor Economics

P.O. Box 7240
Bonn, D-53072
Germany

Edward J. Schumacher

Trinity University - Department of Health Care Administration ( email )

715 Stadium Drive
San Antonio, TX 78212-7200
United States
210-999-8137 (Phone)
210-999-8108 (Fax)

Register to save articles to
your library

Register

Paper statistics

Downloads
65
Abstract Views
1,334
rank
338,089
PlumX Metrics