RDPERMUTE: Stata module to perform a permutation test for the Regression Kink (RK) and Regression Discontinuity (RD) Design
Simon Jäger, Peter Ganong · RePEc: Research Papers in Economics · 2018
rdpermute implements a permutation test for the Regression Kink (RK) and Regression Discontinuity (RD) Design for the one dimensional case of one Outcome Variable (y) and one Assignment Variable (x). By analyzing a set of user defined placebo estimates (placebo_disconts) in and outside the region of a suspected policy kink defined by its position on the x-Axis (true_discont), it tests for the sharp null hypothesis of no effect of the policy on the outcome. The printed results describe the calculated bandwidth at the suspected policy kink, the coefficient of the treatment effect, the classical p-Value for asymptotic inference analysis and the p-Value for our recently proposed randomization test. A list of all calculated information for each placebo estimate is stored in the return value. See Ganong, P. & Jäger, S. (2018), "A Permutation Test for the Regression Kink Design", Journal of the American Statistical Association, 113:522, 494-504.