David, Thanks for your feedback. However, I think if you look at the mean of your output (which, as a minor point, doesn't provide the same data to predict as expand.grid(X1=c(-1,0,1),X2=c(-1,0,1)), you'll see it is very different from the mean of dat$out. Like Ista's previous answer, I think in your case the predict function acts on xxA and xxB (as if renaming the newdata to dat[1:2] in Ista's case) and acts as if they were in their original scale, that is, it doesn't treat the predictors as Z scores. As a result, the yhat values are different from what should be expected.
----------------------------------- Russell S. Pierce, M.A. Visual Cognition Lab Department of Psychology University of California, Riverside 900 University Avenue Riverside, CA 92521 Lab Phone: (951) 827-7399 On Sat, Jan 29, 2011 at 11:10 AM, David Winsemius <dwinsem...@comcast.net> wrote: > ms.res <- glm(out ~ scale(xxA)*scale(xxB), data=dat) > newdata <- predict(rms.res, newdata=data.frame(xxA=c(-1,0,1),xxB=c(-1,0,1))) ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
