Statalist The Stata Listserver


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

Re: st: lrtest again for clarification


From   Richard Williams <Richard.A.Williams.5@ND.edu>
To   statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu
Subject   Re: st: lrtest again for clarification
Date   Fri, 25 Aug 2006 08:47:25 -0500

At 07:24 AM 8/25/2006, Rho YH wrote:
Thanks for the advice, and I've read the article
For clarification, please confirm this
As I specified before,
logistic A B C D E F G
est store A
logistic A B C D E F H I
lrtest a .
Model | Obs ll(null) ll(model) df AIC BIC
-------------+----------------------------------------------------------------
A | 1695 -556.4883 -311.149 9 640.298 689.2169
.. | 1695 -556.4883 -318.3306 10 656.6611 711.0155
------------------------------------------------------------------------------
Then . (the latter) is better as A - . < 0 ?
Both the BIC and AIC tests favor model A.

Incidentally, fitstat (part of the spost9 routines) is a handy program to have here, as it makes it even easier to do these sorts of comparisons and provides additional info.

One other question though - is there any particular reason why G is excluded from the 2nd model? If it were there the models would be nested.

You may also wish to check out the various BIC-related programs written by Paul Millar.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* 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