Go to main content
Did you know? By making a gift to AgEcon Search, you are helping ensure that our small non-profit continues to provide free full-text access to 15,000 visitors a day from 170+ countries
Format
BibTeX
MARCXML
TextMARC
MARC
DublinCore
EndNote
NLM
RefWorks
RIS

Files

Abstract

In this paper we derive the covariance matrix of the matrix quadratic forms S A := X'AX and S B := X'BX, where X' : pxn is normally distributed with E(X 1) = M' and D(vec X') = U o V (U : nxn and V : pxp positive semidefinite), A and B are general (nonrandom) matrices. As a corollary E(SACSB) is presented, for general (nonrandom) matrices A, B and C. All vectDrsand matrices are real.

Details

PDF

Statistics

from
to
Export
Download Full History