Statalist


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

Re: st: Conditional logit


From   "Arne Risa Hole" <arnehole@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Conditional logit
Date   Thu, 1 May 2008 14:24:12 +0100

Rodrigo,

Stata *does* take into account the 'unchosen' alternatives as these
will apear in the denominator of the probabilities of the chosen
alternatives. Which of the two approaches (including all alternatives
vs dropping those that were never chosen) you should use is another
matter: if no one chose an alternative you could argue that this
alternative does not figure in the respondents' choice set and should
therefore be excluded from the model. On the other hand it may have
been considered and found inferior by all respondents. I'd run the
model both including and excluding the unchosen alternatives - if the
results are similar you're ok, if not you have to think about which
model seems the most convincing. The latter is probably more of a
behavioural than a statistical question.

Arne

On 01/05/2008, R.Alegria@lse.ac.uk <R.Alegria@lse.ac.uk> wrote:
> Hi all,
>
> I'm estimating a conditional logit with 150 possible alternatives.
> However, over these 150 possible alternatives only 134 are chosen.
>
> When estimating in Stata with clogit, should I include as my choice set
> the 150 possible alternatives or only the 134 that are actually chosen?
>
> I have some doubts about whether the estimation procedure takes into
> account alternatives that are not chosen by any chooser.
>
> Thanks in advance,
> Rodrigo
>
>
> Please access the attached hyperlink for an important electronic communications disclaimer: http://www.lse.ac.uk/collections/secretariat/legal/disclaimer.htm
>
> *
> *   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/
>
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index