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: mixlogit
From
Arne Risa Hole <[email protected]>
To
statalist <[email protected]>
Subject
Re: st: mixlogit
Date
Wed, 25 Sep 2013 09:25:33 +0100
Hi Ragnhild,
You are welcome. See below for some responses to your follow-up questions:
> I noted, however that you, in your syntax "swithched" from year as the
> "id" variable to idnr. Can you explain to me the reason for this?
> Does your syntax mean that Stata "understand" that it is the same
> individuals that are observed on several occations?
Yes, Stata "understands" that it is the same person making the
choices, as the value of "idnr" is the same for each choice made by
the same doctor.
> Can I also ask you a question regarding the number of Halton
> sequences? The default is 50, but would you recomend increasing it?
I would recommend inceasing this to 500 if you intend to publish the
results. In addition you could estimate a model using e.g. 750 or 1000
draws to check that the results are stable.
Arne
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/