Statalist


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

Re: st: probit & conformability error in inteff


From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: probit & conformability error in inteff
Date   Fri, 2 May 2008 13:17:03 +0100 (BST)

--- Chin-Chih <[email protected]> wrote:
> I was trying to run 'Inteff" to obtain the marginal effects of 
> interactive terms in probit via STATA 10.0. After running the probit 
> command, I tried to run inteff and I got the following message:  
> conformability error r(503); Does anyone know what conformability
> error means and how can I fix it?

You can find out what r(503) means by typing -search r(503)-, than you
will get:

[P]     error . . . . . . . . . . . . . . . . . . . . Return code 503
        conformability error;
        You have issued a matrix command attempting to combine two
        matrices that are not conformable, for example, multiplying
        a 3x2 matrix by a 3x3 matrix.  You will also get this message
        if you attempt an operation that requires a square matrix and
        the matrix is not square.

In your case this could mean two things:
1) -probit- dropped a variable due to multicolinearity and -inteff- did
not accurately pick that up. If that is the case you will have gotten a
warning when you ran  the -probit- command. The solution is to fix your
model so it does not contain any collinear variables.

2) An operation on the variance covariance backfired. This can happen
if you have explanatory variables with wildly different scales, e.g.
income in dollars per year and whether or not someone is female.
Something you could do that might help is to make the scales more
similar, e.g. by dividing the income by 10,000.

Hope this helps,
Maarten

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