Dear S-LIST,
I would appreciate any information you have regarding the magnitude of the
effect of explanatory variables on the dependent when an interaction in spatial
linear regression models is significant.
In CAR models with a continuous dependent variable, I have obtained
significant interactions between a continuous explanatory variable and a factor
variable - using HELMERT contrasts. The conditional scatterplot shows a
positive relationship with factor level 1, and a negative relationship for
factor level 0.
I would like to state the magnitude of effect for each factor level separately.
Your advice welcome.
Kind regards,
Dora
Dora Pearce
PhD student
School of Science & Engineering
University of Ballarat
PO Box 663, Ballarat, Victoria, 3353
Email: dpearce@students.ballarat.edu.au
Ph: (03) 5327 9264
|