SIGNRANK - Wilcoxon signed-rank test The Wilcoxon signed-rank test is a non-parametric statistical hypothesis test used to compare two related samples whether their population median ranks differ [1-4]. SIGNRANK treads NaNs as "Missing values" and ignores these. The current implementation has been validated against wilcox.test of R (v4.0.4). pval = signrank(X,m [, ...]) tests Null-hypothesis that median of x is m. size(m,DIM) must be one, all other dimensions must match those of X pval = signrank(x,y [, ...]) size of x and size of y must match, it is tested whether the difference x-y is significantly different to m=0; pval = signrank(x,y,alpha) pval = signrank(x,y,alpha,tail) pval = signrank(x,y,alpha,tail,DIM) [pval,H,stats] = signrank(...) H=1 indicates a rejection of the Null-hypothesis at a significance level of alpha (default alpha = 0.05). With the optional argument string TAIL, the alternative of interest can be selected. If TAIL is '!=' or '<>' or 'both', the null is tested against the two-sided Alternative `mean (X) ~= mean (Y)'. If TAIL is '>' or 'right', the one-sided Alternative `mean (X) > mean (Y)' is used. Similarly for '<' or 'left', the one-sided Alternative `mean (X) < mean (Y)' is used. The default is the two-sided case. H returns whether the Null-Hypotheses must be rejected. The p-value of the test is returned in PVAL. signrank works on the first non-singleton dimension of X and Y, or on DIM. If no output argument is given, the p-value of the test is displayed. Reference(s): [1] Glenn A Walker, (2002) Common Statistical Methods for Clinical Research (with SAS examples), 2nd edition Chapter 12 The Wilcoxon Signed-Rank Test. [2] https://en.wikipedia.org/wiki/Wilcoxon_signed-rank_test [3] https://math.stackexchange.com/questions/1414794/wilcoxon-signed-rank-test [4] https://de.wikipedia.org/wiki/Wilcoxon-Vorzeichen-Rang-Test
Package: nan