06-24-2015 12:10 PM
Hi! I have a question: how can i 'translate' this RStudio command
> fm9.1<-gls(visual~-1+visual0+time.f+treat.f:time.f, weights=varIdent(form=~1|time.f),data=armd)
in SAS code?
I can't solve this problem. Thanks for your help!
06-24-2015 12:42 PM
It's a regression with heterogeneus variance: visual= visual0 timef timef*treatf without intercept, where timef and treat are factors. Based on generalize least squares (weighted in particular), where the 'w_i' is not equal 1, as usual, but it's equal to the variance of the first level of timef. How can i write this?