Christophe Pallier wrote: > The Wilcoxon paired rank sign test assumes symmetry. > (cf. http://www.basic.northwestern.edu/statguidefiles/srank_paired_alts.html > ) > > ...of differences, and under the null hypothesis. This is usually rather uncontroversial. With only 7 different outcomes for differences (-3:3) you need to pay attention to ties, though. R's wilcox.test will get the asymptotic variance right, but cannot do exact test in that case, so you may want to check out package ExactRankTests.
> Christophe Pallier > > On 5/10/07, Alexander Kollmann <[EMAIL PROTECTED]> wrote: > >> Hello, >> >> given situation: >> >> - pre / post test comparison of discrete, paired data [values can be >> 1,2,3,4]. >> - the data are neither normal distributed nor symetric >> >> Which test should I use to calculate the p-value? Is the wilcoxon rank sum >> test ok ? >> >> >> Alex >> >> ______________________________________________ >> R-help@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. >> >> > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@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. > -- O__ ---- Peter Dalgaard Ă˜ster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 ______________________________________________ R-help@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.