I was going through the Newey West (1987) paper: "A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix" and was trying to understand the proof that this matrix is positive semi definite. Specifically i did not understand the part where they build a symmetric matrix Pij
and equate the postive semi definite property of this matrix with the positive definite propoerty of the Newey West covariance matrix. Could someone help in understanding this please.
Serving the Quantitative Finance Community
-
- FaridMoussaoui
- Posts: 327
- Joined:
- Location: Genève, Genf, Ginevra, Geneva
Re: Proof that Newey West standard error estimator is positive semi defnite
Is that theorem 1 ( [$] \hat{S_{T}} [$] is positive semi-definite)?
-
- atulnahar04
- Posts: 3
- Joined:
-
- FaridMoussaoui
- Posts: 327
- Joined:
- Location: Genève, Genf, Ginevra, Geneva
Re: Proof that Newey West standard error estimator is positive semi defnite
Well, no proof was given there, it just said, have a look to McLeod paper.
Here a screenshot of that proof:
Here a screenshot of that proof:
-
- atulnahar04
- Posts: 3
- Joined:
Re: Proof that Newey West standard error estimator is positive semi defnite
Hi, thanks for this. I was able to find this paper online and understand it.