When the errors are heteroskedastic, then
A)WLS is efficient in large samples, if the functional form of the heteroskedasticity is known.
B)OLS is biased.
C)OLS is still efficient as long as there is no serial correlation in the error terms.
D)weighted least squares is efficient.

Question

Quizplus · Accepted Answer

In the case of heteroskedasticity, OLS becomes inefficient and biased. Weighted least squares (WLS) is a better option, but it requires knowledge of the functional form of the heteroskedasticity. In larger samples, WLS is efficient, and therefore choice A is correct. OLS is still unbiased, but its standard errors are biased, so choice B is incorrect. The presence of heteroskedasticity does not affect the efficiency of the estimator as long as there is no serial correlation in the error terms, so choice C is incorrect.

When the Errors Are Heteroskedastic, Then