I was wondering if someone could help me with this ?
I’ve been trying to do this question but not seeming to get anywhere, I’m guessing it’s something relatively simple?
Thanks for any help
Turn on thread page Beta
You are Here: Home > Forums >< University and university courses >< Science, Technology, Engineering and Maths university courses >< Mathematics
Expectation and Eigenvalues, Statistics question watch
- Thread Starter
- 05-02-2018 11:49
- 07-02-2018 11:43
Well just look at what the diagonal of the covariance matrix is. Then think about how you can simplify that when you know that for i =1,..,p, E(X_i) = 0. Then it should just follow from linearity of expectation when setting X = (X_1 .... X_p).
The second equality is just linear algebra, it applies to a general matrix with entries in R, that trace is equal to sum of eigenvalues. One way you can show this uses det(AB)=det(A)det(B) and that S is symmetric (so diagonalisable).