THE IMPORTANCE OF SAMPLE ATTRITION IN LIFE-CYCLE LABOR SUPPLY ESTIMATION

We examine the importance of possible nonrandom attrition to an econom etric model of life cycle labor supply rising both a Wald test compari ng attriters to nonattriters and variable addition rests based on form al models of attrition. Estimates rising the Panel Study of Income Dyn amics show that nonrandom attrition is of little concern when estimati ng prime-age male labor supply because the effect of attrition is abso rbed into fixed effects in labor supply. The wage measure and instrume nt set have much larger effects on the estimated labor supply function of prime-age men than how one adjusts for panel attrition.