Heteroscedasticity corrected covariance can be used in cases of heteroscedasticity in regression analyses. However, these corrected estimators have no related effect size metrics, meaning only a part of the output could be corrected, while other parts would remain biased. For this reason, this is not yet implemented.

For future implementations the following can be good starting points:

• For heteroscedasticity corrected covariance technical details: Cribari-neto, 2009
• For technical details on robust estimators in general: MacKinnon, J. G. (2012). Thirty years of heteroskedasticity-robust inference. In Recent advances and future directions in causality, prediction, and specification analysis: Essays in honor of Halbert L. White Jr (pp. 437-461). New York, NY: Springer New York.