Interpreting aggregate wage growth: The role of labor market participation

Abstract

A new and easily implementable framework for the empirical analysis of the relationship between aggregate and individual wages is developed. Aggregate real wages are shown to contain three important bias terms: one associated with the dispersion of individual wages, a second deriving from compositional changes in the (selected) sample of workers, and a third reflecting the distribution of working hours. Their importance for interpreting the path of aggregate wages and of the returns to education for recent experience in Britain is highlighted. A close correspondence between the estimated biases and the patterns of differences shown by aggregate wages is established.