How important are fixed effects and time trends in estimating returns to schooling? Evidence from a replication of Jacobson, Lalonde, and Sullivan, 2005

Abstract

A substantial and rapidly growing literature has developed around estimating earnings gains from 2‐year college degrees using administrative data. These papers almost universally employ a person‐level fixed‐effects strategy to estimate earnings premia net of fixed attributes. We note that the seminal piece on which these papers build—Jacobson, Lalonde, & Sullivan, Journal of Econometrics, 2005, 125(1–2), 271–304—provides theoretical and empirical evidence for the importance of additionally differencing out individual time trends. The subsequent literature has not followed suit. Through replication we ask whether this matters. We show that it does, and further that these person‐level time trends need not be computationally burdensome in large administrative data. We recommend them as a unifying econometric standard for future work.