I understand that the Newey-West estimator is an approach to estimate the covariance of the linear regression estimator (OLS) when there are heteroskedasticity and autocorrelation. Should it modify the estimator itself though? In other words, if $$\hat\beta_{\text{OLS}}=\left(X^\prime X\right)^{-1} X^\prime y,$$ then what should $\hat\beta_{\text{NW}}$ be?

  • 2
    $\begingroup$ The point estimator itself remains unaffected, NW is about, as you say, using another covariance estimator. $\endgroup$ – Christoph Hanck Mar 29 '16 at 11:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.