Mark,
I think Melvin is correct. The question is whether any of the higher order
effects (than the ones you modeled) is significant. If it is, then there is
specification error in the power of the estimated dependent.
Best,
Bob
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University
Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf
CV: http://homepages.nyu.edu/~ray1/vita.pdf
----- Original Message -----
From: "Schaffer, Mark E" <[email protected]>
Date: Friday, September 11, 2009 10:02 pm
Subject: RE: st: Reset test
To: [email protected]
> Bob,
>
> > -----Original Message-----
> > From: [email protected]
> > [mailto:[email protected]] On Behalf Of
> > Robert A Yaffee
> > Sent: 11 September 2009 21:09
> > To: [email protected]
> > Subject: Re: st: Reset test
> >
> > Melvyn,
> > Just use the
> > estat ovtest
> > after your regression command. It appears as if the
> > fourth power of the dv is used. You'll be able to tell from
> > the numerator in the associated F test.
>
> Mel's question is different, and interesting. He's saying that he can
> get very different results for his RESET test depending on the order of
> the polynomial used. (Self-plug: you can't control the order of
> polynomial used in Stata's -ovtest- but you can in -ivreset-.)
>
> The questions are, how to interpret this, and is there any literature
> on
> it? I don't know the answers to either question, and I'd also be
> interested to hear from someone who does.
>
> Cheers,
> Mark
>
> > Cheers,
> > Bob
> >
> >
> > Robert A. Yaffee, Ph.D.
> > Research Professor
> > Silver School of Social Work
> > New York University
> >
> > Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf
> >
> > CV: http://homepages.nyu.edu/~ray1/vita.pdf
> >
> > ----- Original Message -----
> > From: Melvyn Weeks <[email protected]>
> > Date: Friday, September 11, 2009 8:50 pm
> > Subject: st: Reset test
> > To: [email protected]
> >
> >
> > > My understanding is that the RESET test in STATA has a default (and
> > > fixed) setting based upon adding a 4th degree polynomial in
> > predicted
> > >
> > > values.
> > >
> > > I can obviously specifiy the test myself.
> > >
> > > However, I have noted that using either a robust or non-robust
> > > variant, that inference can very much depend - especially in small
>
> > > samples - on
> > >
> > > the order of the polynomial.
> > > Does anyone have experience with this and is there any useful
> > > references I should check out.
> > >
> > > M.
> > >
> > > *
> > > * 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/
> > *
> > * 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/
> >
>
>
> --
> Heriot-Watt University is a Scottish charity
> registered under charity number SC000278.
>
>
> *
> * 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/
*
* 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/
