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

st: cdsimeq and two stage conditional maximum likelihood


From   "Takako Yuki" <yuki@ip.rcast.u-tokyo.ac.jp>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: cdsimeq and two stage conditional maximum likelihood
Date   Sat, 5 Jun 2004 11:21:30 +0900

Dear everyone: 

Do anyone know whether STATA has a command for correcting the second
stage standard errors in two stage conditional maximum likelihood(2SCML)
suggested by Rivers and Vuong (1988)?  For the two stage probit least
squares estimation (2SPLS), the CDSIMEQ command implements such
corrections (Keshk, 2003).  But I want to do 2SCML (partly because I
need to use "weight" and the CDSIMEQ does not allow me to use
"aweight").

Or, as econometrical issues, such corrections to standard errors may not
be necessary in 2SCML?  This point seems to be mentioned by Alvarez and
Glasgow (1999, p.150). But I am not sure whether I do not need
corrections to discuss the statistical significance of coefficient
estimates, partly because of Wooldridge (2002, p.474), which says that
standard errors and test statistics are not strictly valid and sounds to
suggest corrections.  

I would appreciate if someone help me on this issue. 

Yuki


*
*   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