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]
Re: st: score test for the parallel regression assumption
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: score test for the parallel regression assumption
Date
Wed, 23 May 2012 08:53:59 -0400
At 04:12 PM 5/22/2012, Brendan Halpin wrote:
On Tue, May 22 2012, Richard Williams wrote:
> The score test is different. It is a LaGrange Multiplier test, and my
> impression (hopefully wrong!) is that Stata does not have many good
> built-in routines for such tests. The SAS documentation for the test is
> at
Hm. I downloaded the helpful paper Stas Kolenikov pointed to the other
day (http://www.citeulike.org/user/ctacmo/article/890474) so there is
every chance I will have a notion of what LaGrange Multipliers are,
before long :-)
LR and Wald tests are easy to do in Stata. I am curious why LM/Score
tests are not better supported (assuming they aren't). Are they
harder to program? Is there little demand for them? There is an old
user-written command called -testomit- which you can get with
-findit-, but its capabilities seem limited.
UCLA has some FAQs on LR, Wald & LM:
http://www.ats.ucla.edu/stat/mult_pkg/faq/general/nested_tests.htm
http://www.ats.ucla.edu/stat/stata/faq/nested_tests.htm
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/