[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: How to do Davidson-Mackinnon P-test in STATA
Marrten -- Thanks for your quick response to my
Here are some more details of the P test. Davidson and
Mackinnon (1981) suggest that if you have 2 different
model specifications that you can fit the data. One
way to choose between non-nested non-linear models is
to use Davidson and Mackinnon P test by estimating the
y(t) = (1 - alpha)f(t) + alpha*ghat(t) + FhatBhat +
f(t) and g(t) are the null and alternative models;
ghat(t) is the fitted values from fitting the model on
FhatBhat is a vector containing the derivatives of f
with respect to B evaluated at Bhat
We can then test if the null hypothesis that alpha is
zero (model f(t) is the better model). t-test can be
used to test this hypothesis.
I hope these details should be helpful for others to
understand the analysis problem I am looking at.
Thanks for any hints or suggestions that you can
--- Maarten buis <firstname.lastname@example.org> wrote:
> --- Angsana Achakulwisut <email@example.com>
> > I wan to use Davidson-Mackinnon
> > P-test to compare different model specifications.
> > I got stuck with the following questions:
> > * Are there any ready-to-use STATA commands or ADO
> > files for this test?
> -findit Davidson-Mackinnon- did show some hits, I am
> not familiar with
> the Davidson-Mackinnon p-test so I can't say if that
> is what you want.
> This immediately leads to a point in the Statalist
> "Please do not assume that the literature familiar
> to you is familiar
> to all members of Statalist. Do not refer to
> publications with just
> minimal details (e.g., author and date). Questions
> of the form "Has
> anyone implemented the heteroscedasticity under a
> full moon test of
> Sue, Grabbit, and Runne (1989)?" admittedly divide
> the world. Anyone
> who has not heard of the said test would not be
> helped by the full
> reference to answer the question, but they might
> well appreciate the
> full reference."
> Hope this helps,
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room Z434
> +31 20 5986715
> Inbox full of unwanted email? Get leading protection
> and 1GB storage with All New Yahoo! Mail.
> * For searches and help try:
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Finding fabulous fares is fun.
Let Yahoo! FareChase search your favorite travel sites to find flight and hotel bargains.
* For searches and help try: