Dear Statalisters:
A new release of -ivreg2-, version 2.1.08, by Baum/Schaffer/Stillman is now
available from the SSC archives.
The main changes:
1. A new option, -savefirst-, to save first-stage regressions for later
display using Stata's -estimates- command.
2. Better handling of collinearities.
3. A bug fix to the -orthog- option when used in conjunction with -cluster-
(see below for details).
4. Various minor bug fixes and presentational changes.
--Mark
Details of the bug referred to in (3): the -orthog- option, combined with
-cluster-, should generate a "C" or "difference-in-Sargan" test statistic
that is robust to arbitrary heteroskedasticity and within-group correlation.
As is standard in Stata, the use of -cluster- with ivreg2 implies -robust-.
I am not sure about general practice, but some of us tend to include
-robust- along with -cluster- anyway, and some of us tend to say just
-cluster-. The bug was that -ivreg2- would produce the correct C test
statistic only if the user also specified -robust-. If -robust- was
omitted, the "difference-in-Sargan" was a difference of a cluster-robust
Sargan and a non-robust Sargan.
Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3294
email: [email protected]
web: http://www.sml.hw.ac.uk/ecomes
-------------------------------------------------------------------
DISCLAIMER
This message is subject to http://www.hw.ac.uk/disclaim.htm
-------------------------------------------------------------------
*
* 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/