R:带领带的精确p值Wilcoxon配对对检验

Question

当存在平局时，如何获得该测试的确切p值?威尔科克斯。当出现这种情况时，Test返回警告，如下所示:

1: In wilcox.test.default(x = c3a0, y = c3a1, alternative = c("two.sided",  :
cannot compute exact p-value with ties
2: In wilcox.test.default(x = c3a0, y = c3a1, alternative = c("two.sided",  :
cannot compute exact confidence interval with ties 

Answer 1

coin::wilcoxsign_test()方法使用两个选项处理平局:Wilcoxon和Pratt。让我引用一下文档(" 0 "参考关系):

对于wilcoxsign_test，默认处理零的方法(0。method = "Pratt")，由于Pratt(1959)，第一阶变换绝对差值(包括零)，然后放弃排名对应于零差。威尔考克森的提议(1949, p. 6)首先放弃零差，然后秩变换剩余的绝对差(0)方法="Wilcoxon"。

从硬币版本1.0-16开始，0。方法参数被替换(现已拆除的)领带。方法参数。当前默认值为零。method = "Pratt"而早期版本有ties.method=HollanderWolfe"，等于零。method = " wilcox ">

https://cran.r-project.org/web/packages/coin/coin.pdf