Does Marriage Boost Men's Wages? Identification of Treatment Effects in Fixed Effects Regression Models for Panel Data

• Activity Number: 103
• Type: Invited
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Social Statistics Section
• Author(s): Michael E Sobel*+
• Companies: Columbia University
• Keywords: causal inference ; fixed effects ; longitudinal data ; marriage premium ; panel data ; unobserved variables

Abstract

Social scientists have generated a large and inconclusive literature on the effect(s) of marriage on men's wages. Researchers use fixed effects regressions for panel data to adjust for selection on unobserved time invariant confounders, interpreting coefficients on the time varying marriage variables as effects. But they do not define these effects or give conditions under which the regression coefficients would warrant a causal interpretation. Consequently, they failed to appropriately adjust for important time varying confounders and misinterpreted their results. The same problem arises in many other research areas. This paper draws on recent work on causal inference with longitudinal data to clarify these problems. A basis set of treatment effects is defined and used to define derived treatment effects. Causal models for panel data with unobserved time invariant confounders are defined and the treatment effects are reexpressed in terms of these models. Ignorability conditions under which the parameters of the causal models are identified from the regression models are given. Even when these hold, a number of interesting and important treatment effects are not identified.