Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: IVPOIS -- Error: Hessian is not positive semidefinite.


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: IVPOIS -- Error: Hessian is not positive semidefinite.
Date   Tue, 18 Dec 2007 17:08:39 -0500

Mohammad Rahman <ippab.research@gmail.com>:

Can you show a set of commands using publicly available data that
reproduces this error?  The help for -ivpois- (on SSC) shows
estimation examples using three datasets avail via:

use http://fmwww.bc.edu/ec-p/data/wooldridge/card, clear
ssc inst ivpois, replace
net get ivp_bwt
use ivp_bwt, clear
net get ivp_cig
use ivp_cig, clear

and -webuse- has access to many more example datasets.

-ivpois- cannot be used for Negative Binomial models.

On Dec 18, 2007 4:51 PM, Mohammad Rahman <ippab.research@gmail.com> wrote:
> Hi,
>
> I have not been successful in using IVPOIS command in Stata 10.  I used the
> same example that is outlined in the help file.  However, every time I am
> getting an error saying: "Hessian is not positive semidefinite (an error
> occurred when bootstrap executed iv_poisson)". The error code is: r(430).
>
> I would really appreciate any help regarding this.
>
> Also, could you give me any pointer how I can use it for Negative Binomial
> models.
>
> Thanks a lot in advance.
>
> Regards,
>
> Mohammad
>
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index