Statalist The Stata Listserver


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

st: RE: Re: Fitstat with switching regression model


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Re: Fitstat with switching regression model
Date   Sat, 16 Dec 2006 12:56:34 -0000

I am unclear on why this is a matter for uncertainty
or speculation or even query. 

In the help for -fitstat-, I read in the first paragraph

"fitstat is a post-estimation command that computes a variety of measures
of fit for many kinds of regression models.  It works after the following:
clogit, cnreg, cloglog, intreg, logistic, logit, mlogit, nbreg, ocratio,
ologit, oprobit, poisson, probit, regress, zinb, and zip.  With the saving()
and using() options, it can also be used to compare fit measures for two
different models." 

You can read the fuller version by typing in Stata 

. rnethelp "http://www.indiana.edu/~jslsoc/stata/spost9_ado/fitstat.hlp";

-movestay- isn't included. That's all there is to it. 

In terms of the original query -- comparing OLS and switching 
regression -- essentially no detail is supplied, so only very 
general comments seem possible. If the response variables are 
the same you could start by plotting the two predictions against
each other and thinking about them. 

Nick 
[email protected] 

Zurab Sajaia
 
> I don't know what particular features of -fitstat- you were 
> going to use but 
> one simple thing that can be done is the Wald or LR test, to 
> test whether 
> rhos are significantly different from zero (in fact, 
> -movestay- reports the 
> results of these tests).
> 
> -movestay- returns more or less all the standard statistics 
> like any other 
> estimation command, -fitstat- is user-written program and I 
> don't know 
> whether it just forks for a limited list of commands or there 
> is something 
> that -movestay- fails to return. If it's second, I'll gladly make the 
> necessary modifications in it.

Quang Nguyen

> > I would like to compare the switching regression model with a simple
> > OLS. To run the switching regression I use the _movestay_ 
> procedure in
> > Stata. After that, I use  _fitstat_ to compare. However, I 
> received a
> > message stating that _fitstat_ doesn't work with _movestay_. I would
> > highly appreciate if you could suggest me a way to compare the
> > switching regression and OLS modeld.

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index