topic Re: Automatic Backwards elimination in Proc Mixed in Statistical Procedures

Automatic Backwards elimination in Proc Mixed

yiferic — Thu, 26 May 2011 16:58:25 GMT

I think there's supposed to be a way to have sas automatically do backwards elimination in proc reg, but is there a way to do it in proc mixed? Our main issue is we have a lot of variables and we are not sure whether the cross terms are significant or not.

Re: Automatic Backwards elimination in Proc Mixed

lvm — Fri, 27 May 2011 01:55:08 GMT

There is no direct way to do this with MIXED. This is a nontrivial matter, and there are lots of things to consider. There is a nice procedure called GLMSELECT for linear model selection, but only for fixed effects. A fascinating macro has been written to do what you are asking. See:
http://www2.sas.com/proceedings/forum2007/191-2007.pdf
for a description. I have not used it, and it looks like it takes a lot of effort to set up and get to run (initially). But the output, including graphics, look great.

Re: Automatic Backwards elimination in Proc Mixed

yiferic — Fri, 27 May 2011 19:39:35 GMT

Thanks, will try it out and update.

Re: Automatic Backwards elimination in Proc Mixed

yiferic — Tue, 31 May 2011 19:24:11 GMT

I'm going to stick with glmselect, the script posted by Prof Fernandez is not very easy to use.