When you say a cross-country analysis, do you mean that each country is a
unit of analysis? If so, then the number is a bit small for the robust
option. (For alternatives, you might like to investigate the use of
quantile regression (qreg, sqreg)). If there are many units within a
country, then you might want to consider some kind of multi-level
analysis, eg xtpoisson.
Tim
Jun S Kang <[email protected]>
Sent by: [email protected]
06/07/2006 17:32
Please respond to
[email protected]
To
[email protected]
cc
Subject
st: RE: Appropriate number of samples for POISSON regression with ROBUST
option
Hello,
I’m trying to conduct a cross-country analysis using POISSON with ROBUST
option. The results of the regression are consistent with my expectation.
However, the number of samples used in the analysis is only 45 countries.
I’m wondering whether the number is appropriate to conduct the poisson
analysis.
Thanks
Jun
*
* 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/
