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 at the end of May, and its replacement, statalist.org is already up and running.


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

st: RE: about qvf


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: about qvf
Date   Wed, 31 Mar 2010 17:55:34 +0100

My guess is that you are doing nothing wrong. -qvf- is a user-written
command, as a complete question would have made clear. I don't think
-qvf- is being maintained by its original authors and I don't think
there was either a claim that -qvf- matched -glm- detail for detail. In
short, it looks as if you want -qvf- to do something it does not
support. 

Nick 
n.j.cox@durham.ac.uk 

Arina Viseth

I am using glm to run a fractional logit regression: the command I am
using is, glm y x1 x2 x3, family(binomial) link(logit) robust. y is my
fractional dependant variable.
I would like to control for the possible endogeneity of one of my
regressor, x1, using qvf and instrumental variable t1. However when I
type qvf y x1 x2 x3 (t1 x2 x3), I have the message "y not 0/1 for
Bernoulli model". 

May I please ask for your help/suggestion on what I am doing wrong here?

*
*   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