[R] Repost: Estimation when interaction is present: How do I get get the parameters from nlme?

2006-06-15 Thread John S. Walker
Gday, This is a repost since I only had one direct reply and I remain mystified- This may be stupidity on my part but it may not be so simple. In brief, my problem is I'm not sure how to extract parameter values/effect sizes from a nonlinear regression model with a significant interaction

Re: [R] Repost: Estimation when interaction is present: How do I get get the parameters from nlme?

2006-06-15 Thread Martin Henry H. Stevens
Hi John, I think a solution is to 1. recode A and B as a single factor, AB, with four levels, 2. define each fixed effect as a function of AB minus the intercept (e.g. ed50 ~ as.factor(AB)-1). 3. extract the tTable as a data.frame with summary(model)$tTable. I will be interested to see what