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: likihood function is not concave in clogit model


From   Nina YIN <yinnina.ccer@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: likihood function is not concave in clogit model
Date   Fri, 29 Jun 2012 16:09:05 +0200

Hi Maarten,

I am sorry that I didn't make it clear. Here the group identifier is
the identifier for choice situations. Therefore, it is constant within
one choice situation. I guess it's the same reason as in mixlogit or
conditional fixed logit model that we couldn't include individual
characteristics because of no within-group variance, right?

You are right, I might made some mistakes in my data preparation and
model. I will check that and discuss with others. Thanks a lot!

Best,
Nina

On Fri, Jun 29, 2012 at 2:58 PM, Maarten Buis <maartenlbuis@gmail.com> wrote:
> On Fri, Jun 29, 2012 at 2:23 PM, Nina YIN wrote:
>> As you suggested, I tried use products and year fixed effect
>> separately, however, it says that the year dummies omitted because of
>> no within-group variance.
>> The year dummies is the same as individual attributes which cannot be
>> added in this type of model, right?
>
> That really depends on your data and your model, but to me it sounds
> like you did something(*) wrong. I would not expect time to be
> constant within an individual.
>
> -- Maarten
>
> (*) The problem is that that "something" could be just about anything,
> from a problem in the data preparation, to model specification, and
> anything in between. Diagnosing such vague problems is much much
> easier in a face-to-face setting than via forum like statalist. So I
> would recommend to find someone within your institute that can help
> and make an appointment with him or her. Be prepared to leave that
> appointment with an entirely different model.
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
>
> http://www.maartenbuis.nl
> --------------------------
> *
> *   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/



-- 
Best Regards,
Nina YIN


Toulouse School of Economics
Manufacture des Tabacs
21 Allee de Brienne
Toulouse, 31000, France
Tel: 0033-(0)5 6123 8348
*
*   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