The heterogeneous effects of the minimum wage on employment across states

摘要

This paper studies the relationship between the minimum wage and the employment rate in the US using the framework of a panel structure model. The approach allows the minimum wage, along with some other controls, to have heterogeneous effects on employment across states which are classified into a group structure. The effects on employment are the same within each group but differ across different groups. The number of groups and the group membership of each state are both unknown a priori. The approach employs the C-Lasso technique, a recently developed classification method that consistently estimates group structure and leads to oracle-efficient estimation of the coefficients. Empirical application of C-Lasso to a US restaurant industry panel over the period 1990–2006 leads to the identification of four separate groups at the state level. The findings reveal substantial heterogeneity in the impact of the minimum wage on employment across groups, with both positive and negative effects and geographical patterns manifesting in the data. The results provide some new perspectives on the prolonged debate on the impact of minimum wage on employment.