= Heteroskedasticity-consistent standard errors
{wiki}
<Heteroskedasticity-consistent standard errors> use an estimated regression covariance that remains consistent when error variances vary across observations. For ordinary least squares, the basic sandwich estimate is $(X^TX)^{-1}X^T\operatorname{diag}(\hat\varepsilon_i^2)X(X^TX)^{-1}$. The resulting standard errors are square roots of its diagonal entries. This is a regression application of a <sandwich covariance matrix>.
Back to article page
