Statalist


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

Re: st: Bivariate Probit


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Bivariate Probit
Date   Fri, 23 May 2008 11:26:14 -0400

Chiara Mussida <cmussida@gmail.com>:
I think that means transitions from unemployed (U) to employed (E) or
not in the labor force (N). Offhand, that sounds like a case for a
competing risks survival analysis; see
http://home.fsw.vu.nl/m.buis/wp/survival.html
http://www.iser.essex.ac.uk/teaching/degree/stephenj/ec968/
help st

but maybe you only have one observation over time.  In that case,
-mlogit- and others in that family may be of use.

On Fri, May 23, 2008 at 10:44 AM, Chiara Mussida <cmussida@gmail.com> wrote:
>> On Fri, May 23, 2008 at 8:46 AM, Chiara Mussida <cmussida@gmail.com> wrote:
>>> Dear All,
>>> I'm tryng to allow correlation between risks related to the labour market.
>>> I have 2 dependent binary variables for transitions from U to E, and
>>> from U to N, respectively. The covariates are the same for both the
>>> equations:
>>> is a bivariate probit the proper choice for my purpose (correlation
>>> between risks)? I have 2 dependent variables and the same RHS of the
>>> regression.
>>>
>>> Thanks a lot,
>>> chiara
*
*   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