Talk:Multivariate normal distribution

From Wikipedia, the free encyclopedia
Jump to: navigation, search
WikiProject Statistics (Rated C-class, Top-importance)
WikiProject icon

This article is within the scope of the WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page or join the discussion.

C-Class article C  This article has been rated as C-Class on the quality scale.
 Top  This article has been rated as Top-importance on the importance scale.

Best Linear Unbiased Predictor[edit]

The document states:

When plotted in the x,y-plane the distribution appears to be squeezed to the line ** expression here ** as the correlation parameter ρ increases. This is because the above expression is the best linear unbiased prediction of Y given a value of X.[3]

But the expression is obviously not the BLUP. Take the correlation to be .0000001, and both means to be zero. The expression then states that the value of X itself is essentially the BLUP of Y, when the number 0 would be a much better predictor. — Preceding unsigned comment added by (talk) 18:29, 5 September 2012 (UTC)
17:52, 29 January 2013 (UTC)

Wrong PDF formula[edit]

(I'm sorry, I don't know how to edit the png with the formula or else I would edit the main page). The pdf is mis-stated --- the constant term should be (2 pi)^{-k/2} (not (2pi)^{-1/2} as it is now) — Preceding unsigned comment added by (talk) 19:01, 7 May 2013 (UTC)


I reckon the entropy formula could be wrong when compared to the referenced paper and the Differential_entropy wiki page. It should be

H = 1/2 * log(2 * PI * e^N det(COV))


The determinant bars were previously missing in the infobox; I just changed it to an equivalent but I think clearer form. Epistemenical (talk) 22:23, 1 October 2013 (UTC)