RobustSE

The RobustSE R package implements the generalized information matrix (GIM) test to detect model misspecification described in King and Roberts (2015). “Robust standard errors” are used in a vast array of scholarship to correct standard errors for model misspecification. However, when misspecification is bad enough to make classical and robust standard errors diverge, assuming that it is nevertheless not so bad as to bias everything else requires considerable optimism. And even if the optimism is warranted, settling for a misspecified model, with or without robust standard errors, will still bias estimators of all but a few quantities of interest. The accompanying article shows how to use robust standard errors as diagnostic tools via the GIM statistic (based on differences between robust and classical variance estimates), with practical illustrations via simulations and real examples. Open source software is available at https://github.com/IQSS/RobustSE and implements the test for linear, Poisson, and negative binomial regressions.