Local Composite Quantile Regression for Regression Discontinuity

We introduce the local composite quantile regression (LCQR) to causal inference in discontinuity (RD) designs. Kai, Li and Zou study efficiency property of LCQR, while we show that its nice boundary performance translates accurate estimation treatment effects RD under a variety data generating processes. Moreover, propose bias-corrected standard error-adjusted t-test for inference, which leads confidence intervals with good coverage probabilities. A bandwidth selector is also discussed. For illustration, conduct simulation revisit classic example from Lee. companion R package rdcqr developed.