In the notation of Section 4.7.2, show that, when third- and higherorder cumulants are neglected, the cubes
Question:
In the notation of Section 4.7.2, show that, when third- and higherorder cumulants are neglected, the cubes of the least squares residuals have covariance matrix cov(R iR jR k
, R lRmR n
) given by
κ
3 2 {ρ
i,jρ
k,lρm,n
[9] + ρ
i,lρ
j,mρ
k,n
[6]}, here taken to be of order n 3 × n 3
. Show that, if ν = n − p is the rank of ρ
i,j
, then wijk,lmn = ρi,lρj,mρk,n [6]/36 − ρi,jρk,lρm,n [9]/ {18 (v + 4)}
Fantastic news! We've Found the answer you've been seeking!
Step by Step Answer:
Related Book For
Tensor Methods In Statistics Monographs On Statistics And Applied Probability
ISBN: 9781315898018
1st Edition
Authors: Peter McCullagh
Question Posted: