Title: Estimating the Causal Efiects of Education on Wage Inequality Using IV Methods and Sample Selection Models
Abstract: We propose instrumental variables and semiparametric estimators to solve the problem of selection bias in comparisons of wage inequality across schooling groups. These estimators provide ∞exible schemes for the identiflcation of (conditional) average treatment efiects (ATE) on various inequality measures, including conditional variance and interquantile spreads. Our latent index framework captures the efiect of a binary schooling choice on inequality. We also show how symmetry assumptions for the joint distributions of error terms in the outcome and selection equations, along with kernel weighting schemes, can be used to identify the ATE on inequality. Asymptotic theory is derived for the proposed estimators; a simulation study indicates that both estimators perform well in flnite samples. Using college proximity as an instrument for schooling, we flnd little evidence that college education increased the degree of wage inequality in 1976. This runs contrary to the conventional OLS results.
Publication Year: 2005
Publication Date: 2005-01-01
Language: en
Type: article
Access and Citation
Cited By Count: 8
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot