The problem comes from mixing up general linear model (LM) theory to compute
B with the classical anova estimators. The two methods use different
approaches to solving the normal equations. LM theory uses any generalized
inverse of X'X to solve the normal equations. Yours comes from ginv() whic
Hey,
I am modelling a linear regression Y=X*B+E. To compute the effect of “group”
the B-values of the regressors/columns that code the interaction effects (col.
5-8 and col. 11-14, see below) have to be weighted with non-zero elements
within the contrast "Group 1" minus "Group 2" (see below). My
2 matches
Mail list logo
