Statalist


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

Re: st: probit questions


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: probit questions
Date   Wed, 25 Jun 2008 17:25:52 +0100 (BST)

--- "Sun, Yan (IFPRI)" <Y.SUN@CGIAR.ORG> wrote:
> I have couple of questions about the Probit model. My dependent
> variable is a 0/1 binary choice (1=invest in technology, 0=no
> investment) for user groups, independent variables are user groups'
> characteristics (around 20).
> 1) Which model is correct one: Probit or Logit? What is the STATA
> command for checking this?

The differences are very minor, I believe that the tails are slightly
fatter for the logistic distribution than the normal (or was it the
other way round?), anyhow you won't find any difference with only 60
observations. So your choice should be quided by convenience and
conventions in your discipline. I like -logit- because I like odds
ratios, but economists tend to like -probit-. 

> 2) I have small observations (total 170 observations, but valid obs.
> Is only around 60 for all independent variables), sometimes the
> regression does not report report "wald chi2" statistics. What is
> the reason for this?

In these kinds of models trying to estimate the effects of 20
covariates with 60 datapoints just means that you are pushing your data
too hard. 

Related to this, loosing almost 2/3 of your already small dataset seems
very problematic to me. Do you realy need all 20 covariates? Also you
might consider Multiple Imputation, which in Stata is among other
implemented as the -ice- package by Patrick Royston (2004 2005a 2005b
2007). Although, given this large proportion of missing data, this too
has it's own problems.

> 3) I got a note after right after the regression, which says "8
> failures and 7 successes completely determined", what does this
>  means?

It means that there are observations with the same values on all
covariates who are all failures or all successes. Standard maximum
likelihood can't handle these cases, -exlogistic- can, see 
-help exlogistic-.

Hope this helps,
Maarten

Royston, P. 2004. Multiple imputation of missing values. Stata Journal
4(3): 227241.
http://stata-journal.com/article.html?article=st0067

Royston, P. 2005a. Multiple imputation of missing values: update. Stata
Journal 5(2): 188201.
http://stata-journal.com/article.html?article=st0067_1

Royston, P. 2005b. Multiple imputation of missing values: Update of
ice. Stata Journal 5(4): 527-536. 
http://stata-journal.com/article.html?article=st0067_2

Royston, P. 2007. Multiple imputation of missing values: further update
of ice, with an emphasis on interval censoring. The Stata Journal 7(4):
445-464 
http://stata-journal.com/article.html?article=st0067_3

-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      __________________________________________________________
Sent from Yahoo! Mail.
A Smarter Email http://uk.docs.yahoo.com/nowyoucan.html
*
*   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