Panel Data Quantile Regression for Treatment Effect Models

In this study, we develop a novel estimation method for quantile treatment effects (QTE) under rank invariance and stationarity assumptions. Ishihara (2020 Ishihara, T. (2020), “Identification Estimation of Time-Varying Nonseparable Panel Data Models Without Stayers,” Journal Econometrics, 215, 184–208. DOI: https://doi.org/10.1016/j.jeconom.2019.08.008.[Crossref] , [Google Scholar]) explores identification the nonseparable panel data model these assumptions proposes parametric based on minimum distance method. However, when dimensionality covariates is large, using process computationally demanding. To overcome problem, propose two-step regression methods. We then show uniform asymptotic properties our estimator validity nonparametric bootstrap. The Monte Carlo studies indicate that performs well in finite samples. Finally, present two empirical illustrations, to estimate distributional insurance provision household production TV watching child cognitive development.