R-beta: offset code in glm....

Mike Meyer (mikem@stat.cmu.edu)
Wed, 03 Jun 1998 15:34:50 -0400


Message-Id: <199806031934.PAA18786@desire.stat.cmu.edu>
To: r-help@stat.math.ethz.ch
Subject: R-beta: offset code in glm....
Date: Wed, 03 Jun 1998 15:34:50 -0400
From: Mike Meyer <mikem@stat.cmu.edu>

I'm trying delve into the offset code in glm, and I have to admit I'm getting 
lost.

My particular concern is that if you do something like

	glm( fred ~ wilma, offset=barney, data=betty)

then the offset is not found if  barney is a component of the data frame 
betty. (If you do the same thing with weights, then the weight is found in the 
data frame).

I don't know if this is a design decision, and I can't follow the logic of the
	model.offsets
code.  

I'm willing to try to fix the behaviour of the offset code, but I could use 
some help understanding what all the current code.  In particular is the 
function called
	model.extract
(which seems to play with offsets?) used anywhere.

Thanks, --Mike

Mike Meyer, Department of Statistics, Carnegie Mellon University


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._