Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

re: st: mann-whitney test

From   David Airey <>
Subject   re: st: mann-whitney test
Date   Thu, 4 May 2006 15:04:10 -0500

Sorry, but I'm confused! I ran two treatments and 32 subjects (organised
in group of 4) participated to each treatment (10 periods). This means
that I have only 8 independent observations in each period for each
treatment. How should be my dataset to run the mann-whitney test? If I
consider 320 observations in each treatment, I cannot say that they are
independent. How should I perform the test in this case?
Sounds like if all you want is a p-value, you could cram your data through a mann-whitney test. Ignoring that you might be better off with a model matching your design, average each group of 4 patients' scores at each period (if each person was measured), then average over their 10 periods. Then run the mann-whitney test on the 8 averages in one treatment versus the other 8. You are ignoring variation (over time, individual) this way but it was what you wanted. Maybe you sampled over time rapidly just for the sake getting a more accurate measure. Maybe the group of 4 was necessary...anyway, yes if you want the mann-whitney test you do need the averages given your description.

* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index