Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Re: Non parametric anova

From   Nick Cox <>
Subject   Re: st: Re: Non parametric anova
Date   Tue, 30 Aug 2011 16:45:22 +0100

It's hard to see that Friedman can be appropriate but not -ologit-.

I'd use an analysis based on means and wave a flag of caution.


On Tue, Aug 30, 2011 at 4:39 PM, Arti Rayit <> wrote:
> I have any experiment which involves measuring pain scores on patients in the
> range 0(1)4 at 4 time periods with 2 drug therapies and I am stuck with the
> analysis. I considered ologit but I do not think that it is appropriate for
> repeated measures and I could find nothing in the 'xt' suite of programs. For
> each treatment Friedman (SJ-5-2) shows an effect of time but does not allow me
> to compare the treatments.
> I would be grateful for any advice. I am using Stata 12.
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index