Re: [R] Setting contrasts

Hi David, You attach the dataset, which creates a copy of it. You set the contrasts on the copy, but in your models, you reference the dataset explicitly. You should set the contrasts directly in the data (and for your sake and your students, would encourage not using attach() ). contrasts(Eyse

[R] Setting contrasts

I have been having trouble understanding the difference between "contrasts(Group) <- contr.sum" and options(contrasts = c("contr.sum","contr.poly"). They both seem to say that they have done what I want, but only the latter works. The reason why the question arises is tha,t using Fox's Anova,

Re: [R] setting contrasts for a logistic regression

w_poet wrote: Hi everyone, I'm doing a logistic regression with an ordinal variable. I'd like to set the contrasts on the ordinal variable. However, when I set the contrasts, they work for ordinary linear regression (lm), but not logistic regression (lrm): ddist = datadist(bin.time, exp.loc) op

[R] setting contrasts for a logistic regression

Hi everyone, I'm doing a logistic regression with an ordinal variable. I'd like to set the contrasts on the ordinal variable. However, when I set the contrasts, they work for ordinary linear regression (lm), but not logistic regression (lrm): ddist = datadist(bin.time, exp.loc) options(datadist=