Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: xtmepoisson postestimation
From
Owen Gallupe <[email protected]>
To
[email protected]
Subject
Re: st: xtmepoisson postestimation
Date
Wed, 29 Aug 2012 11:37:15 -0400
Hi,
I'm interested in the question proposed by Jihane but assuming an
outcome variable was used for which a Poisson model was expected to be
suitable (i.e., not a dichotomous variable). In that case, how would
one appropriately test the model fit of a multilevel Poisson model?
Thanks.
Owen Gallupe
On Tue, Aug 28, 2012 at 6:05 PM, David Greenberg <[email protected]> wrote:
> IF you your outcome variable is binary, why are you assuming a Poisson
> distribution? David Greenberg, Sociology Department, NYU
>
> On Tue, Aug 28, 2012 at 10:32 AM, jihane ben farhat <[email protected]> wrote:
>> Dear Statalist,
>>
>> could you please help me to test that my xtmepoisson model fits properly.
>> The syntax is as below:
>>
>> xi:xtmepoisson outcome i.age i.gender i.origin || project:, exp(y) re irr
>>
>> With outcome = yes or no
>> and y is my follow-up duration.
>>
>> I mean, I would like to see if my residuals and the random effect follow a
>> Normal distribution, and then how to compare Predict vs observed data?
>>
>> Thank you for your help.
>> Regards,
>> Jihane
>> *
>> * 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/
> *
> * 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/
*
* 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/