With heteroskedastic errors, the weighted least squares estimator is BLUE. You should use OLS with heteroskedasticity-robust standard errors because
A)this method is simpler.
B)the exact form of the conditional variance is rarely known.
C)the Gauss-Markov theorem holds.
D)your spreadsheet program does not have a command for weighted least squares.

Question

Quizplus · Accepted Answer

The exact form of the conditional variance is rarely known with heteroskedastic errors, therefore it is best to use OLS with heteroskedasticity-robust standard errors. While weighted least squares is BLUE, it is not necessary in this case and OLS with robust standard errors is a simpler alternative. The Gauss-Markov theorem does not hold with heteroskedastic errors. The lack of a command in a spreadsheet program for weighted least squares is not a determining factor.

With Heteroskedastic Errors, the Weighted Least Squares Estimator Is BLUE