Correcting for Survival Effects in Cross Section Wage Equations Using NBA Data

Cross sectional employment data is not random. Individuals who survive to a longer level of tenure tend to have a higher level of productivity than those who exit earlier. This result suggests that in cross sectional data high productivity workers are over-sampled at high levels of tenure. In wage equations using cross sectional data, results could be biased from the over sampling of high productive workers at long levels of tenure. This survival effect in cross sectional data could possibly bias the coefficient on tenure upwards. We explore techniques to correct for survival bias using a panel study of National Basketball Association players. In particular we focus on a modified Heckman selectivity bias procedure using duration models to correct for survival bias. Key Words: