Volume 33, Number 2 (Spring) 1998: Attrition in Longitudinal Surveys

Ziliak, James P., and Thomas J. Kniesner. 1998. "The Importance of Sample Attrition in Life Cycle Labor Supply Estimation." Journal of Human Resources 33(2):507-530.

We examine the Importance of possible nonrandom attrition to an econometric model of life cycle labor supply using both a Wald test comparing attriters to nonattriters and variable addition tests based on formal models of attrition. Estimates using the Panel Study of Income Dynamics show that nonrandom attrition is of little concern when estimating primeage male labor supply because the effect of attrition is absorbed into fixed effects in labor supply. The wage measure and instrument set have much larger effects on the estimated labor supply function of prime-age men than how one adjusts for panel attrition.

James P. Ziliak is an assistant professor of economics at the University of Oregon, Eugene. Thomas J. Kniesner is a professor of economics at Indiana University, Bloomington. The authors thank three anonymous referees, Greg Duncan, Joel Horowitz, Arie Kapteyn, Tom MaCurdy, Peter Schmidt, Marno Verbeek, Jeff Wooldridge, and participants at the BLS Conference on Attrition Bias in Longitudinal Surveys, the Fifth International Conference on Panel Data, and the Tilburg University Center-VSB Saving Workshop for constructive criticisms. The authors are grateful for the financial support from Indiana University's Office of International Programs and Indiana University's Office of the Vice President for Research and the University Graduate School. The data used in this article can be obtained beginning July 1, 1998 until June 30, 2001 from James P. Ziliak Department of Economics, University of Oregon, Eugene, OR 97403-1285, USA.