Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: reg3 and estimation problem


From   Mark Schaffer <M.E.Schaffer@hw.ac.uk>
To   statalist@hsphsun2.harvard.edu, "Mooi, E.A. (Erik)" <emooi@feweb.vu.nl>
Subject   Re: st: reg3 and estimation problem
Date   Mon, 17 May 2004 13:41:32 +0100 (BST)

Erik,

Quoting "Mooi, E.A. (Erik)" <emooi@feweb.vu.nl>:

> Dear Statalisters,
> 
> I would like to estimate a model using the reg3 procedure. I have
> two equations, one where performance is dependent upon
> innovativeness and 8 other variables, and innovativeness which is
> dependent upon the same 8 variables.

It looks like you have an identification problem.  You have 2 endogenous 
variables (faa and fab), each with its own equation, and 8 exogenous 
variables.  Both the faa and the fab equation have 9 regressors, one 
endogenous and 8 exogenous.  Your structural model has 2x9=18 structural 
coefficients.  If you write the model in reduced form with just exogenous 
variables on the RHS, you have 2 RF equations x 8 exogenous regressors = 
16 RF coefficients.  18 > 16, so the model is underidentified.  Each 
equation taken individually is also underidentified, because you don't 
have any exogenous variables that are excluded from either of the 
equations.

What you need are some exclusion restrictions that identify the model.  
For example, if fak were a regressor in the fab eqn but not the faa 
equation, you could use it as an excluded instrument for fab; the faa 
equation would be identified and estimable [estimatable?] using single-
equation IV.  To estimate the system using 3SLS, you would also need at 
least one exclusion restriction that identifies the fab equation as well.

--Mark

> The instruments at my disposal
> are theoretically not very good.
> 
> Thus using the 3SLS estimation procedure does not appear to be a
> very good option. OLS is technically possible but since the errors
> are correlated in the model described above the OLS assumptions are
> violated. Doe anyone know of a way to estimate the problem described
> above?
> 
> Regards,
> 
> Erik A. Mooi
> 
> PS: the stata model is: reg3 (faa = fab fac fae faf fag fah fai faj2
> fak) (fab = faa  fac fae faf fag fah fai faj2 fak), nodfk corr
> (unstructured) ols    where faa is performance and fab
> innovativeness.
> 
> 
> 
> Vrije Universiteit Amsterdam
> Faculty of Economics and Business Administration
> Department of Marketing
> De Boelelaan 1105
> 1081 HV Amsterdam
> The Netherlands
> Tel: 031204449862
> Fax: 031204446005
> http://staff.feweb.vu.nl/emooi/
> 
> *
> *   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/
> 



Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3008
email: m.e.schaffer@hw.ac.uk
web: http://www.sml.hw.ac.uk/ecomes
________________________________________________________________

DISCLAIMER:

This e-mail and any files transmitted with it are confidential
and intended solely for the use of the individual or entity to
whom it is addressed.  If you are not the intended recipient
you are prohibited from using any of the information contained
in this e-mail.  In such a case, please destroy all copies in
your possession and notify the sender by reply e-mail.  Heriot
Watt University does not accept liability or responsibility
for changes made to this e-mail after it was sent, or for
viruses transmitted through this e-mail.  Opinions, comments,
conclusions and other information in this e-mail that do not
relate to the official business of Heriot Watt University are
not endorsed by it.
________________________________________________________________
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index