[S] Mixed model for binomial data

Brian Beckage (bb2@acpub.duke.edu)
Mon, 27 Jul 1998 14:07:51 -0400


I have two questions: First, is there a way to do a mixed model
anova using a link to the binomial distribution?

Second, when using anova() on a glm object (with family=binomial),
is there an easy way to get the type III analysis of deviance table (order
independent) instead of the type I, without having to manually change the
order of the model?

I'm using version 3.3 for on a sparc workstation.

Thanks for your help,
Brian

-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news