I suppose you could use regress q19 brand [weight=weight]
Tony
Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Data Analytics Corp.
Sent: Wednesday, January 27, 2010 8:54 AM
To: [email protected]
Subject: st: t-test for weighted data
Hi,
Suppose I have a data set with four variables from a market research
survey: consumer ID, brand (say two brands, A and B), Q19 (responses to
question 19 on a 1 - 7 scale), and a weight. I need to compare the mean
response on Q19 for the two brands. With unweighted data, I would
simply use a t test - no problem. But with the weights I have an
issue. The t test does not accept weights. If I do the test by
constructing my own t-stat, the numerator would be just the difference
in the weighted means - no problem there. The issue is the standard
error for the difference in weighted means. Does anyone know a source
on this standard error? Does anyone know of a function (or have one)
for doing a t-test for weighted data?
Thanks,
Walt
--
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
[email protected]
www.dataanalyticscorp.com
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
