Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: -poisson postestimation- chi2 discrepancy


From   graupel75@gmail.com
To   Statalist <statalist@hsphsun2.harvard.edu>
Subject   st: -poisson postestimation- chi2 discrepancy
Date   Thu, 27 Sep 2012 09:38:51 +0800

Dear 'listers,

I am working on Poisson models, and using -estat gof- I obtain:

         Deviance goodness-of-fit =  301.3502
         Prob > chi2(269)         =    0.0852

         Pearson goodness-of-fit  =  1135.374
         Prob > chi2(269)         =    0.0000

My data do not appear to be horribly over-dispersed (alpha from
-nbreg- is 3.39e-07), (variance = 3.6, mean 1.8).
I suspect the discrepancy could be due to the very large df (it's a
collapsed Cox model), but the Stata manual for -poisson
postestimation- doesn't provide any clarity on when one gof might be
more apppropiate. Alternatively, the model could be very poorly
specified, but only options I know of are SSC's -fitstat-.

Any suggestions?

cheers-
Andrew Lover
______________________________________________
Epidemiologist
Centre for Infectious Disease Epidemiology Research (CIDER)
Saw Swee Hock School of Public Health
National University of Singapore
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index