[R] Interpreting the result of a Wilcoxon (Mann-Whitney U) test

[PIKAL Petr]

Hi

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Filipe Correia
> Sent: Wednesday, October 02, 2013 10:32 PM
> To: Charles Determan Jr
> Cc: r-help at r-project.org
> Subject: Re: [R] Interpreting the result of a Wilcoxon (Mann-Whitney U)
> test
> 
> Hi,
> 
> Thank you for your answer Charles.
> 
> On Wed, Oct 2, 2013 at 6:50 PM, Charles Determan Jr <deter088 at umn.edu>
> wrote:
> > When you chose a different alternative argument you are asking a
> > different null hypothesis.
> 
> I was considering the null hypothesis was expressed through the "mu"
> argument. I think I got this idea from R's docs where it states that
> "the null hypothesis is that the distributions of x and y differ by a
> location shift of mu" (when "a" and "b" are both given and "paired" is
> FALSE).  Does the "alternative" argument also influence the null
> hypothesis in some way that I may be missing?
> 
> My understanding was that by using the "alternative" argument one would
> be expressing the alternative hypothesis only.
> 
> > You are looking at a two-tailed, lesser than, and greater than
> > hypotheses.  Which one you chose is dependent upon your initial
> > question.  Are you asking generically if your two populations (a and
> > b) are different?  Are you asking if a > b or a < b?
> 
> Well, I guess I'm asking all of the three... :) Not with the intent to
> choose which one fits, but because I was experimenting and making sure
> I really understand how I could use R's implementation of the Wilcoxon
> test. But I'm intrigued that the answer to "are a and b different" is
> not consistent with "is a less than b"... Maybe my understanding of the

Your understanding of statistical test is not correct. When asking /a is not equal b/ you are "splitting" probability of alternative hypothesis to both sides, with asking /a is lower than b/ probability of alternative hypothesis is only at one side of distribution. It is really not a question of R but a question of basic statistics.

If some program gave you same answer to those questions you shall get rid of it immediately.

Regards
Petr


> function's arguments and return values is not correct? :\
> 
> 
> Thanks,
> Filipe
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.