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]

Re: st: IV estimation in a negative binomial framework


From   Arka Roy Chaudhuri <gabuisi@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: IV estimation in a negative binomial framework
Date   Fri, 12 Aug 2011 13:31:40 -0700

Thank so much for your suggestions. Abhimanyu, please correct me if I
am wrong but the -ssm- procedure does not seem to allow for negative
binomial in its family sub command- it only allows for binomial and
poisson.

I had a question about -ivpois- vs -qvf-.Is there any reason for
-ivpois- to be theoretically better than -qvf-? I looked at the
example in the ivpois help file which shows that ivpois performs
better than qvf but in my case qvf seems to perform better than
ivpois. So I was wondering if there are any theoretical reasons for
why ivpois is better than qvf and the essential differences between
the two.

Thanks a lot again for all your suggestions.

Regards,
Arka

On Wed, Aug 10, 2011 at 7:51 AM, Austin Nichols <austinnichols@gmail.com> wrote:
>
> Arka Roy Chaudhuri <gabuisi@gmail.com>
> -glm- with a log link does not need an assumption that the conditional
> variance is equal to the conditional mean to be consistent, nor does
> its IV analog.  See -ivpois- on SSC and
> http://www.stata.com/meeting/boston10/boston10_nichols.pdf
>
> On Tue, Aug 9, 2011 at 5:03 PM, Arka Roy Chaudhuri <gabuisi@gmail.com> wrote:
> > Hi,
> >
> >
> > I am analyzing a model where my dependent variable is a count
> > variable, specifically the number of riot cases in a district. Since
> > the variance of the dependent variable is quite high compared to the
> > mean I plan to use the negative binomial distribution. However my
> > independent variable is endogenous and I would like to use a
> > instrument variable analysis. Unfortunately I have been unsuccessful
> > in finding any program which implements IV in a negative binomial
> > context. Could somebody please advice me how to implement IV
> > estimation in a negative binomial framework? I would really appreciate
> > any help in this regard.
> >
> > Thanks,
> > Arka
> >
> *
> *   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/


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