In Stata, -robust- means Huber/White/sandwich estimator of variance correcting the standard errors only for heteroscedasticity.
The following is a website discussing the corrections for the standard errors (it discusses corrections for panel data, nonetheless several are used for cross-sectional data as well, and I found it quite interesting for non-experienced researchers/Stata users -- Stata commands are cited, too, and discussed)
http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/se_programming.htm
Huber, P. J. (1967), �The behavior of maximum likelihood estimates under nonstandard conditions�, in Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1, University of California Press, Berkeley, CA, pp. 221-233.
White, H., 1984, �A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test of Heteroskedasticity,� Econometrica 48, 817-838.
At 02.33 31/01/2007 -0500, Joan Holand wrote:
>I'm running a loglinear model (categorical data; Stata V.9, Windows XP)
>using the -glm- (option: fam(pois)) and the -poisson- command.
>
>I have a question about the option -robust-: When is it reasonable to
>use this option? I have read that it makes the confidence intervall
>narrower. Are there other reasons for / benefits of using this option?
*
* 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/
