Thank you marrten. So, if you had to set it up backward, how would you go
about doing that? I have read the documentation for switchr and I'm still
unclear.
george
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Maarten Buis
Sent: Wednesday, August 01, 2007 12:35 PM
To: [email protected]
Subject: st: RE: How to set up switching regression model
--- george m hoffman wrote:
> I have a dataset with 24 paired measurements (Y1 and Y2) on 100
> subjects. I am trying to regress y1 on y2, with the added complication
> that the y2 measurement was made with one of two different
> instruments, whose identity was not recorded with the measurement. So,
> I have wo sets of measurements
> (y1 and y2a) and (y1 and y2b) on each subject. The instrument was not
> changed within subjects.
>
> It seems that swithcing regression would help solve this puzzle, but I
> can't set it up correctly in my mind or at the stata keyboard.
I think a switching regression is more appropriate if y1 were measured with
one of two instruments. Switching regression is used for cases when the
explained variable consists of two (or more) unobserved groups. This seems
more a case of measurement error in the explanatory variable. This doesn't
solve your problem though...
Hope this still helps a bit,
Maarten
-----------------------------------------
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
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
*
* 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/
