Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Random effects probit starting values


From   "Stephen P. Jenkins" <[email protected]>
To   [email protected]
Subject   st: Random effects probit starting values
Date   Tue, 17 Sep 2002 12:13:35 +0100 (GMT Daylight Time)

On Mon, 16 Sep 2002 17:39:49 -0500 Weihua Guan <[email protected]> wrote:

> --Wiji Arulampalam <[email protected]> wrote:                    
> 
> > I have just run a random effects probit using the same data on Limdep
> > as well as stata7 and get very different results. I should be most
> > grateful if someone could tell me whether I am doing something wrong
> > please. Limdep gives a reasonable rho but stata does not!
> 
> After exchanging emails with Wiji privately, I think the problem can be solved
> by choosing appropriate starting values for -xtprobit-.

and then he set out how to run -xtprobit- using alternative starting 
values from the default ones, the key lines being:

> . probit sue lague
> . mat b = e(b)
> . local rho = .7
> . local lnsig2u = ln(`rho'/(1-`rho'))
> . mat b = b, `lnsig2u'
> . xtprobit sue lague, i(ind1) quad(12) from(b, copy)

To this message, Wiji responded
> Thank you very much for the useful reply. I actually do not
> understand why stata does not take the starting values from an 
> ordinary probit?

I would like to second this query -- why are the -xtprobit- starting 
values for the b coefficients not the 'ordinary' pooled probit ones?
Surely this would be much more 'effective'?  (And robust to bunging in 
any default value for rho, e.g. 0.7).  After all, random effects 
estimates do not typically differ hugely from the pooled probit ones.

Supplementary questions:
* what /are/ the default starting values that are used for -xtprobit-?
  [I suspect that all betas set to zero, but can't recall seeing this
    in Ref Manuals under this entry, and what about the lnsig2u (rho)?]
* what are the default starting values that are used for -xtlogit-, and
  for other related programs such as -xtclog- and -xttobit- and so on?


Stephen
----------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research (ISER)
University of Essex, Colchester, CO4 3SQ, UK
Tel: +44 (0)1206 873374. Fax: +44 (0)1206 873151.
http://www.iser.essex.ac.uk

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index