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-oprobit using the cmp command


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: IV-oprobit using the cmp command
Date   Thu, 5 Apr 2012 14:57:59 -0500

On Thu, Apr 5, 2012 at 9:35 AM, Peter Gambrill <petergambrill@gmail.com> wrote:
> I am trying to using Instrumental variables using a probit
> specification. The command I have found is the "cmp" command, I just
> wondered if anyone had experience of using this and could help me with
> this estimation.
>
> My endogenous variable is a measure of gender identity. This is a
> discrete variable that has a scale of 7 to 33.
>
> Gender Identity = constant + instruments + error
>
> The second stage dependant variable is a measure of subjective well
> being on a scale of 1 to 36
>
> Subjective well-being = constant + controls + gender identity + error
>
> Can anyone give some advice on how I might achieve this estimation
> using stata?

Oh come on. Don't overcomplicate things. If both ranges are filled up
reasonably well, treat them as continuous and run the whole thing as
-ivregress-. Otherwise, you'd be running into problems with a HUGE
number of ancillary parameters (thresholds) that would be difficult to
identify, especially on the extreme ends, where you may have less than
a handful of observations.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
*   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