Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Problem with -gdecomp- using probit
From 
 
<[email protected]> 
To 
 
<[email protected]> 
Subject 
 
st: Problem with -gdecomp- using probit 
Date 
 
Thu, 18 Apr 2013 13:21:17 +0100 
Dear all,
I am trying to do a variable-specific decomposition on the results of a
probit regression. I am using the -gdecomp- command available from SSC
(ssc install gdecomp, replace). This also requires -margeff- to be
installed. For both commands I am using what I believe are the latest
versions (Version 2.2.0, 20 August 2009). 
When a run the decomposition on the probit I get the following error:
. gdecomp group: probit un hh_size foreign married schl_e age age2
= invalid name
r(198);
I get the same error message when I run -gdecomp- for a logit. But the
decomposition works fine when I run it on a linear regression (which is
however the wrong regression for my data): gdecomp group :  regress y x1
x2 
I don't think there's anything wrong with my model or the data, as the
probit estimation runs fine on its own and the -margeff- command also
works fine following the -probit- estimation. 
Any ideas as to what may be going on??!!
Thanks in advance,
Vassilis
PS: I am aware of the 'nldecompose- command, but this doesn't seem to
offer an option for a variable-specific decomposition...
===============================================
Dr Vassilis Monastiriotis
Hellenic Observatory, European Institute, LSE 
email: [email protected] 
===============================================
Please access the attached hyperlink for an important electronic communications disclaimer: http://lse.ac.uk/emailDisclaimer
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/