search for: mginv

...assume I can live with "only approximations". In another thread, Thorsten Hothorn suggested for glm (slightly edited) library(multcomp) set.seed(290875) # a factor at three levels group <- factor(c(rep(1,10), rep(2, 10), rep(3,10))) # Williams contrasts contrasts(group)<-zapsmall(mginv(contrMat(table(group), type="Will"))) # a binary response z <- factor(rbinom(30, 1, 0.5)) # estimate the model gmod <- glm( z ~ group, family=binomial(link = "logit")) summary(gmod) # exclude the intercept # Should be the following, but does not work due to a confirmed #...

This is only partly a question about R, as I am not quite sure about the underlying statistical theory either. I have fitted a non-linear mixed-effects model with nlme. In the fixed part of the model I have a factor with three levels as explanatory variable. I would like to use Tukey HSD or a similar test to test for differences between these three levels. I have two grouping factors:

I suppose that multcomp in R and multicomp in S-Plus are related and it appears that it is possible to use multicomp with lme in S-Plus given the following correspondence on s-news sally.rodriguez at philips.com 12:57 p.m. 24/04/03 -0400 7 [S] LME summary and multicomp.default() Is it possible to use multicomp with lme in R and if so what is the syntax from a simple readily available

...ntervals for a glm based on the normal approximation. Torsten --------------------------------------------------------------------- library(multcomp) set.seed(290875) # a factor at three levels group <- factor(c(rep(1,10), rep(2, 10), rep(3,10))) # Williams contrasts contrasts(group) <- mginv(contrMat(table(group), type="Will")) # a binary response z <- factor(rbinom(30, 1, 0.5)) # estimate the model gmod <- glm( z ~ group, family=binomial(link = "logit")) # exclude the intercept summary(csimtest(coef(gmod)[2:3], vcov(gmod)[2:3,2:3], cmatrix...