Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Re: How to perform a Vuong test in STATA v10 on Panel Data in Fixed effects model?


From   mantoshkinas <mantoshkinas@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: How to perform a Vuong test in STATA v10 on Panel Data in Fixed effects model?
Date   Wed, 11 May 2011 13:41:58 +0200

How to perform a Vuong test in STATA v10 on Panel Data in Fixed effects model?

I need to compare 2 similar types of regressions and the literature in
my field (Accounting & Finance) indicates that it's good to use the
Vuong test (Vuong Z-statistics or likelihood ratio test for model
selection) to compare which of those 2 regressions has a statistically
higher R-squared (not by just comparing the absolute difference
between R-squareds of the models).

STATA has the Vuong test but it is used only in binomial, negative
binomial and Poisson regressions. My models and the models in those
studies that use Vuong do not contain binomial variables as the
dependent variables. In particular, my dependent variable in both
regressions is annual Stock (Security) Returns of a company and the
independent variables in one regression are Accounting Earnings
(measured as Net Income) & change in Accounting Earnings (change in
Net Income) and Cash Flow from operations and the change in the cash
flow from operations in the other one.

I'd be so grateful if someone could indicate how to compare R-squareds
in those regressions using a statistical test rather than just looking
at the absolute difference between R-squared with bare eye.

Sincerely-
Mantoshkinas
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index