NonlinearDiD: Staggered Difference-in-Differences with Nonlinear Outcomes

Implements difference-in-differences estimators for staggered treatment adoption with binary, count, and other nonlinear outcomes. Extends Callaway and Sant'Anna (2021) <doi:10.1016/j.jeconom.2020.12.001> to handle the fundamental identification challenges that arise with nonlinear outcome models (logit, probit, Poisson) in heterogeneous treatment timing designs. Provides group-time average treatment effects on the treated (ATT), aggregation schemes, and pre-treatment parallel trends tests appropriate for nonlinear settings. Methods include doubly-robust semiparametric estimators, nonparametric bounds, and an odds-ratio DiD approach for binary outcomes. Methods extend Callaway and Sant'Anna (2021) <doi:10.1016/j.jeconom.2020.12.001>, Roth and Sant'Anna (2023) <doi:10.3982/ECTA19255>, and Wooldridge (2023) <doi:10.1093/ectj/utad016>.

install.packages("NonlinearDiD")

Try the NonlinearDiD package in your browser