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: Vuong test for nested linear models
From
Greenfish Wu <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Vuong test for nested linear models
Date
Sun, 9 Feb 2014 13:24:44 -0800 (PST)
Thank you very much John! That's very helpful!
Regards,
Cindy
On Sunday, February 9, 2014 2:35 PM, John Antonakis <[email protected]> wrote:
Hi:
You don't need a Vuong test here. Because you are adding one parameter,
the test of b3 = 0 is the test you want. That is simply the test of the
significance of the parameter estimate. This is equivalent to the nested
F-test:
sysuse auto
nestreg : reg price (mpg) (weight)
The F-change test for adding weight is equivalent to the t-test^2 of the
parameter, i.e.,
dis (_b[weight]/_se[weight])^2
You can still use the lrtest after OLS.
reg price mpg
est store one
reg price mpg weight
est store two
lrtest one two
Best,
J.
__________________________________________
John Antonakis
Professor of Organizational Behavior
Director, Ph.D. Program in Management
Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305
http://www.hec.unil.ch/people/jantonakis
Associate Editor:
The Leadership Quarterly
Organizational Research Methods
__________________________________________
On 09.02.2014 19:33, Cindy wrote:
> Hi, do anyone know how to do Vuong test (Vuong 1989) for model
selection of
> two nested linear models in Stata? It seems that people use Vuong test
> mostly for non-nested models. But Vuong (1989) covers both nested and
> non-nested models. Following are my two models:
>
> Model 1: Y=a0+a1X1+a2X2+e
> Model 2: Y=b0+b1X1+b2X2+b3X3+v
>
> Both models are OLS regressions. I need to test how significant the
> incremental adjusted R2 in model 2 is from adding X3 (my variable of
> interest) to model 1.
>
> Also, it seems that a likelihood ratio test could be used to test nested
> models, too. But when I looked up the code in stata (lrtest), it says
that
> it’s applicable for maximum likelihood models only.
>
> Thank you very much!!
>
>
>
> --
> View this message in context:
http://statalist.1588530.n2.nabble.com/Vuong-test-for-nested-linear-models-tp7580482.html
> Sent from the Statalist mailing list archive at Nabble.com.
>
> *
> * 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/
*
* 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/
*
* 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/