An Application of the Kronecker Product of Matrices in Multiple Regression

Publisher Website
Google Scholar
Abstract
The theoretical basis of fitting the multiple regression of 1 particular variate on 2 sets of determining variates in succession is discussed. The procedure is shown to be equivalent to taking the multiple regression of this variate on a set of variates derived by taking the Kronecker product of the 2 sets. The properties of the Kronecker product are used to determine conveniently the sums of squares for regression and the standard deviations of the regression coefficients. The technique is illustrated by a worked example.

This publication has 1 reference indexed in Scilit:

  • Complex Experiments
    Journal of the Royal Statistical Society Series B: Statistical Methodology, 1935