Date:         Sun, 24 Nov 2002 21:51:23 -0800
Reply-To:     Gregor <gregor.gorjanc@BFRO.UNI-LJ.SI>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Gregor <gregor.gorjanc@BFRO.UNI-LJ.SI>
Organization: http://groups.google.com/
Subject:      Distribution of residuals from generalized LM with response from
              gamma distribution
Content-Type: text/plain; charset=ISO-8859-1

Hello!

I'm performing analysis with GENMOD procedure in SAS. This procedure
allows us to model the data which don't 'obey' the normal
distribution. My questions are:

- How should the residuals be distributed if response commes from
gamma distribution ?
- Which (type) residuals should I analyse (there are quite some:
deviance, Pearson,...)?

Thanks in advance, Gregor.