> ComRades: > > I have a glm where interest lies in the estimated mean levels of the > response Y for every level of factor Year (regardeless of statistical > significance of the factor), when the effect of other factors have been > accounted for. The model is of the form: > > fit<-glm(Y~Year+Mo+Area+Ship+Eff,family=gaussian(link="log"),data=data) > > where Year is categorical and has T levels (labeled 1 to T in the data). > Help much appreciated on how to extract these 'standardised' annual > estimates of Y and their standard errors. > > Rubén
Answering my own question. The problem was that I should write fit<-glm(Y~as.factor(Year)+as.factor(Mo)+as.factor(Area)+as.factor(Ship) +Eff,family=gaussian(link="log"),data=data) then fit$coeff will give me want I wanted, a standardised measure of the effect of Year on Y when other measurable influences has been accounted for. Thanks anyway, Rubén ______________________________________________ R-help@stat.math.ethz.ch 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.
