[BioC] Mann Whitney

[Naomi Altman]

The Wilcoxon test is a permutation test.  We don't actually do the 
permutations, because the p-values are tabulated.

However, because it is a permutation test, the smallest possible 
p-value is 1/#permutations.  So for tiny sample sizes (e.g. 3) you 
cannot get significant results.

--Naomi


At 12:21 PM 12/11/2007, Patricia Garcia wrote:
>Hi
>I'm trying to use a Mann-Whitney test in a PCR data, like this:
>
>
># Case the samples are similar:
>x1 <- c(19.0370805,17.51822,18.524912)
>y1 <- c(20.541484,22.039175,20.542968)
>w1 <- wilcox.test(x1,y1, paired = FALSE, alternative = c("two.sided"))
>
>
>         Wilcoxon rank sum test
>
>     data:  m and f
>     W = 0, p-value = 0.1
>     alternative hypothesis: true location shift is not equal to 0
>
># Case the samples are not similar:
>x2 <- c(3.9934205,    3.499646,    4.489782)
>y2 <- c(20.541484,22.039175,20.542968)
>w2 <- wilcox.test(m,f, paired = FALSE, alternative = c("two.sided"))
>
>
>         Wilcoxon rank sum test
>
>     data:  m and f
>     W = 0, p-value = 0.1
>     alternative hypothesis: true location shift is not equal to 0
>
>
>
>I obtain the same result: pvalue > 0.05, so i don't reject the null
>hypothesis, that both samples came from the same distribution.
>If i test other numbers the result is the same always.
>Thanks.
>
>_______________________________________________
>Bioconductor mailing list
>Bioconductor at stat.math.ethz.ch
>https://stat.ethz.ch/mailman/listinfo/bioconductor
>Search the archives: 
>http://news.gmane.org/gmane.science.biology.informatics.conductor

Naomi S. Altman                                814-865-3791 (voice)
Associate Professor
Dept. of Statistics                              814-863-7114 (fax)
Penn State University                         814-865-1348 (Statistics)
University Park, PA 16802-2111