From: Uwe Ligges <ligges_at_statistik.tu-dortmund.de>

Date: Tue, 03 May 2011 10:39:04 +0200

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. Received on Thu 05 May 2011 - 06:25:10 GMT

Date: Tue, 03 May 2011 10:39:04 +0200

On 03.05.2011 10:33, JP wrote:

> Thanks Uwe,

*>
**> How do I calculate the Z score and r value - please (once I have the p values)?
*

Actually you calculate the p value from the statistics rathger than vice versa. And pairwise.wilcox.test uses wilcox.test to calculate the separate tests and adjusts the p values for multiple testing later on. That's why I said you can manually run wilcox.test to get the separate statistics.

Uwe Ligges

*>
*

> Many Thanks

*> JP
**>
**>
**>
**> 2011/5/2 Uwe Ligges<ligges_at_statistik.tu-dortmund.de>:
**>> To get the statsitics, you will have to run each wilcox.test manually. the
**>> pairwise... version just extracts the p-values and adjusts them.
**>>
**>> Uwe Ligges
**>>
**>>
**>> On 28.04.2011 15:18, JP wrote:
**>>>
**>>> Hi there,
**>>>
**>>> I am trying to do multiple pairwise Wilcoxon signed rank tests in a
**>>> manner similar to:
**>>>
**>>> a<- c(runif(1000, min=1,max=50), rnorm(1000, 50), rnorm(1000, 49.9,
**>>> 0.5), rgeom(1000, 0.5))
**>>> b<- c(rep("group_a", 1000), rep("group_b", 1000), rep("group_c",
**>>> 1000), rep("group_d", 1000))
**>>> pairwise.wilcox.test(a, b, alternative="two.sided",
**>>> p.adj="bonferroni", exact=F, paired=T)
**>>>
**>>> This gives me the following output:
**>>>
**>>> group_a group_b group_c
**>>> group_b<2e-16 - -
**>>> group_c<2e-16 0.25 -
**>>> group_d<2e-16<2e-16<2e-16
**>>>
**>>> (which is kind of expected since group_b and group_c have similar
**>>> distributions)
**>>>
**>>> I have found that when doing a wilcoxon signed ranked test you should
**>>> report:
**>>>
**>>> - The median value (and not the mean or sd, presumably because of the
**>>> underlying potential non normal distribution)
**>>> - The Z score (or value)
**>>> - r
**>>> - p value
**>>>
**>>> My questions are:
**>>>
**>>> - Are the above enough/correct values to report (some places even
**>>> quote W and df) ? What else would you suggest?
**>>> - How do I calculate the Z score and r for the above example?
**>>> - How do I get each statistic from the pairwise.wilcox.test call?
**>>>
**>>> Many Thanks
**>>> JP
**>>>
**>>> ______________________________________________
**>>> 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.
**>>
*

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. Received on Thu 05 May 2011 - 06:25:10 GMT

Archive maintained by Robert King, hosted by
the discipline of
statistics at the
University of Newcastle,
Australia.

Archive generated by hypermail 2.2.0, at Thu 05 May 2011 - 07:00:06 GMT.

*
Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help.
Please read the posting
guide before posting to the list.
*