Determinants of Pay in the NHL A Quantile Regression Approach

Using data from the pre-2004-2005 lockout period, we use quantile regression to estimate the earnings function of forwards and defensemen in the National Hockey League (NHL). We find that the explanatory power of Mincer's earnings equation is smaller for low-paid players than for high-paid stars. More importantly, we find significant differences in the returns to measures of performance and other variables across the conditional earnings distribution. Our estimation results suggest that the conditional expectation model used in previous studies misses some of the subtleties of the earnings determination process in professional hockey.