Prev: FPC Sample Size Power?
Next: using proc export/dbms=xls and excel lost date format
From: Ryan on 26 Feb 2010 21:37
On Feb 26, 2:41 pm, v.bal...(a)GMAIL.COM (Vishal Bali) wrote:
> I have used Proc Genmod and Repeated Subject statement to obtain robust
> standard errors in Poisson and negative binomial regression. Could anyone
> please tell me something  about the STATEMENT AND possible SYNTAX that can be
> used to obtain robust standard errors in Zero inflated Poisson and Zero
> inflated negative binomial regression?

Vishal,

I do not know the solution, but I suspect the solution might involve
running your zero-inflated models in the NLMIXED procedure, rather
than the GENMOD procedure. While it is true that the GENMOD procedure
in SAS 9.2 is capable of running a zero-inflated poisson model, I do
not think you can include a repeated measures statement in the same
model. I also read that zero inflated poisson and zero inflated
negative binomial models can be run in the CATMOD procedure, but I
don't know much about that procedure to say whether or not it can
provide what you need. Dale Mclerran has shown how to run zero-
inflated models with nested designs (in case that's what you're
interested in), though I'm not sure if that's what you want. You
haven't provided any information about your data. Anyway, I suggest
you look through the SAS archives. Maybe if you write back with more
details about your data/design, you will obtain more help.

Ryan
 | 
Pages: 1
Prev: FPC Sample Size Power?
Next: using proc export/dbms=xls and excel lost date format