Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: RE: NPTREND problem

From   "Nick Cox" <>
To   <>
Subject   RE: st: RE: NPTREND problem
Date   Tue, 12 Nov 2002 12:28:33 -0000

Paul O'Brien
> The treatments are ethinly estradiol (EE) 20mcg v EE 30 mcg
> and response is
> weight change, so I think your first response was right. Is that so?

No, I don't think so. What you were trying was to use
the frequencies of response categories
in -nptrend-, but it is for a measured response
variable. You could look at these data in
various ways, for example by -expand-ing on -pop-
and doing a -ranksum-, but the results look
equally supportive of the null. Arguably, whoever
did not collect or threw away the precise
weight information was discarding any fine
structure there might be.


*   For searches and help try:

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