Thank you akk. I know it is not statistically sounded to check the distribution of response before glm. I will check the distribution of xmodel$residuals later on.
About the program problem. It can print summary(xmodel) but not confint(xmodel) by amending my code as suggested by Bill Venables. Regards, CH On 5/7/07, Ben Bolker <[EMAIL PROTECTED]> wrote: > <Bill.Venables <at> csiro.au> writes: > > > > > Finally, I'm a bit puzzled why you use glm() when the simpler lm() would > > have done the job. You are fitting a linear model and do not need the > > extra paraphernaila that generalized linear models require. > > > > Bill Venables. > > > > Perhaps the original poster is confused about the difference > between general (a la PROC GLM) and generalized (glm) linear > models? > > The code is also a little puzzling because the same tests > seem to be run whether p>0.05 or not. Perhaps the code > will eventually be written to log-transform the data > if it fails the normality test? > > [ hint: ?boxcox in the MASS package might be a better way > to go ] > > Ben Bolker > > ______________________________________________ > 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. > -- "The scientists of today think deeply instead of clearly. One must be sane to think clearly, but one can think deeply and be quite insane." Nikola Tesla http://www.macgrass.com ______________________________________________ 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.