This is only tangentially related to Stata.
I have been asked to comment on the methodology of yesterday's paper in the
[online] Lancet by Les Roberts, et al., estimating excess deaths in Iraq at
100,00 since the US invasion. The authors used a randomized household
cluster sample survey. Data were analyzed with Stata, along with other
software, so it is not irrelevant to this list They used GLMs to estimate
relative- and attributable risk. This is a part of the study on which I feel
I do not have competence to adequately assess, though comments on any parts
of the methodology would be apreciated.
If any of the epimemiologists on the list could comment on the methodology,
it would be apreciated:
http://image.thelancet.com/extras/04art10342web.pdf
Obviously, this is a very loaded issue and we want to get it right.
Truth-in-advertising: I am anti-war and mantain an anti-war web site:
http://psychoanalystsopposewar.org/ORR.htm
I MAY write a web piece on this survey. If you make substantive comments and
would like me NOT to attribute by name, please say so.
Thanks,
Stephen Soldz
Director, Center for Research, Evaluation, and Program Development
Boston Graduate School of Psychoanalysis
1581 Beacon St.
Brookline, MA 02446
[email protected]
http://soldzresearch.com/stephensoldz
*
* 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/
