TherARTpackage provides functions for Approximate Randomization Tests with a Small Number of Clusters introduced in “Randomization tests under an approximate symmetry assumption” (Canay, Romano, and Shaikh, 2017) and further described in “On the implementation of Approximate Randomization Tests in Linear Models with a Small Number of Clusters” (2021) by Cai, Canay, Kim, and Shaikh.

You can install rART using the following command:

devtools::install_github("mwt/rART")

or by simply visiting the Github repository HERE. The help file illustrates how the regressions are run, how to compute p-values, and how to compute confidence intervals using the algorithms developed by Cai, Canay, Kim, and Shaikh (2021).