目的

pairwise.t.test を土台として，代表値の差の多重比較を行う

使用法

pairwise.wilcox.test <- function (x, g, p.adjust.method = p.adjust.methods, paired = FALSE, exact=TRUE, ...)

引数

exact   同順位がある場合に coin ライブラリの wilcox_tets で正確な P 値を得る（デフォルトで TRUE）
それ以外の引数は，pairwise.t.test の引数に準ずる

ソース

インストールは，以下の 1 行をコピーし，R コンソールにペーストする
source("http://aoki2.si.gunma-u.ac.jp/R/src/pairwise.wilcox.test.R", encoding="euc-jp")

# 代表値の差の多重比較（対比較）
pairwise.wilcox.test <- function (x, g, p.adjust.method = p.adjust.methods,
        paired = FALSE, exact=TRUE, ...)
{
        DNAME <- paste(deparse(substitute(x)), "and", deparse(substitute(g)))
        g <- factor(g)
        p.adjust.method <- match.arg(p.adjust.method)
        METHOD <- if (paired) "paired wicoxon tests" else "wilcoxon tests"
        compare.levels <- function(i, j) {
                xi <- x[as.integer(g) == i]
                xj <- x[as.integer(g) == j]
                if (paired) {
                        ok <- complete.cases(xi, xj)
                        xi <- xi[ok]
                        xj <- xj[ok]
                }
                else {
                        xi <- xi[!is.na(xi)]
                        xj <- xj[!is.na(xj)]
                }
                if (exact && !paired) {
                        library(coin)
                        x <- c(xi, xj)
                        g <- factor(rep(1:2, c(length(xi), length(xj))))
                        pvalue(wilcox_test(x ~ g, distribution="exact"))
                }
                else
                        wilcox.test(xi, xj, paired = paired, ...)$p.value
        }
        PVAL <- pairwise.table(compare.levels, levels(g), p.adjust.method)
        ans <- list(method = METHOD, data.name = DNAME, p.value = PVAL,
                p.adjust.method = p.adjust.method)
        class(ans) <- "pairwise.htest"
        ans
}


使用例

> attach(airquality)

	The following object(s) are masked _by_ .GlobalEnv :

	 Month 

> Month <- factor(Month, labels = month.abb[5:9])
> pairwise.wilcox.test(Ozone, Month)

	Pairwise comparisons using wilcoxon tests 

data:  Ozone and Month 

    May     Jun     Jul     Aug    
Jun 0.57884 -       -       -      
Jul 0.00011 0.07103 -       -      
Aug 0.00055 0.11668 1.00000 -      
Sep 0.47271 1.00000 0.00423 0.01900

P value adjustment method: holm 
> pairwise.t.test(Ozone, Month)

	Pairwise comparisons using t tests with pooled SD 

data:  Ozone and Month 

    May     Jun     Jul     Aug    
Jun 1.00000 -       -       -      
Jul 0.00026 0.05113 -       -      
Aug 0.00019 0.04987 1.00000 -      
Sep 1.00000 1.00000 0.00488 0.00388

P value adjustment method: holm 
> pairwise.wilcox.test(Ozone, Month, p.adj = "bonf")

	Pairwise comparisons using wilcoxon tests 

data:  Ozone and Month 

    May     Jun     Jul     Aug    
Jun 1.00000 -       -       -      
Jul 0.00011 0.11838 -       -      
Aug 0.00061 0.23336 1.00000 -      
Sep 1.00000 1.00000 0.00528 0.02715

P value adjustment method: bonferroni 
> pairwise.t.test(Ozone, Month, p.adj = "bonf")

	Pairwise comparisons using t tests with pooled SD 

data:  Ozone and Month 

    May     Jun     Jul     Aug    
Jun 1.00000 -       -       -      
Jul 0.00029 0.10225 -       -      
Aug 0.00019 0.08312 1.00000 -      
Sep 1.00000 1.00000 0.00697 0.00485

P value adjustment method: bonferroni 
> detach()