[R] Wilcoxon Rank Sum Test.

[Achim Zeileis]

On Thu, 28 Jun 2007 14:18:52 -0700 Nordlund, Dan (DSHS/RDA) wrote:

> 
> > -----Original Message-----
> > From: r-help-bounces at stat.math.ethz.ch 
> > [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Marcus
> > Vinicius Sent: Thursday, June 28, 2007 1:32 PM
> > To: r-help at stat.math.ethz.ch
> > Subject: [R] Wilcoxon Rank Sum Test.
> > 
> > Dear,
> > 
> > I'm using R software to evaluate Wilcoxon Rank Sum Test and 
> > I' getting one
> > Warning message as this:
> > 
> > > C1dea_com
> >  [1] 1.000 0.345 0.200 0.208 0.508 0.480 0.545 0.563 0.451 
> > 0.683 0.380 0.913
> > 1.000 0.506
> > > C1dea_sem
> >  [1] 1.000 0.665 0.284 0.394 0.509 0.721 0.545 0.898 0.744 
> > 0.683 0.382 0.913
> > 1.000 0.970
> > 
> > 
> > > wilcox.test(C1dea_sem,C1dea_com, paired = TRUE, alternative 
> > = "two.sided")
> > 
> >         Wilcoxon signed rank test with continuity correction
> > 
> > data:  C1dea_sem and C1dea_com
> > V = 45, p-value = 0.009152
> > alternative hypothesis: true mu is not equal to 0
> > 
> > Warning message:
> > Cannot compute exact p-value with zeroes in: 
> > wilcox.test.default(C1dea_sem,
> > C1dea_com, paired = TRUE, alternative = "two.sided")
> > 
> > What is happening?
> > 
> > Best Regards,
> > 
> > Marcus Vinicius
> > 
> 
> Marcus,
> 
> It means that you have one or more pairs of observations (5 in your
> case) where the difference is 0.  The wilcox.test can only compute an
> approximate p-value under these circumstances.

...while wilcox.exact() from package "exactRankTests" can evaluate the
permutation distribution correctly.
Z

> Hope this is helpful,
> 
> Dan
> 
> Daniel J. Nordlund
> Research and Data Analysis
> Washington State Department of Social and Health Services
> Olympia, WA  98504-5204
> 
> ______________________________________________
> R-help at stat.math.ethz.ch 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.
>