Individual and Time Effects in Nonlinear Panel Data Models with Large N , T

Fixed effects estimators of panel models can be severely biased because of the wellknown incidental parameters problem. We develop analytical and jackknife bias corrections for nonlinear models with both individual and time effects. For asymptotics where the time-dimension (T ) grows with the cross-sectional dimension (N), the time effects introduce additional incidental parameter bias. As the existing bias expressions apply to models with only individual effects, we derive the appropriate corrections. The basis for the corrections are asymptotic expansions of the fixed effects score and estimator for panel models with incidental parameters in both individual and time dimensions. These expansions apply to M-estimators with concave objective functions, which cover fixed effects estimators of the most popular limited dependent variable models such as logit, probit, Tobit and Poisson models. We therefore extend the use of large-T bias adjustments to an important class of models.