R实现Fisher's exact test精确检验

tomorrow

下面用R语言实现上面的检验：
> x=c(1,9,11,3)
> alle<-matrix(x, nrow=2)
> fisher.test(alle,alternative ="two.sided")

        Fisher's Exact Test for Count Data

data:  alle
p-value = 0.002759
alternative hypothesis: true odds ratio is not equal to 1
95 percent confidence interval:
0.0006438284 0.4258840381
sample estimates:
odds ratio
0.03723312
通过> help(fisher.test) 来查看使用说明，alternative = "two.sided"是双侧检验，可以根据说明进行调整为单侧'"greater"' or '"less"'.


fisher.test              package:stats              R Documentation

Fisher's Exact Test for Count Data

Description:

     Performs Fisher's exact test for testing the null of independence
     of rows and columns in a contingency table with fixed marginals.

Usage:

     fisher.test(x, y = NULL, workspace = 200000, hybrid = FALSE,
                 control = list(), or = 1, alternative = "two.sided",
                 conf.int = TRUE, conf.level = 0.95,
                 simulate.p.value = FALSE, B = 2000)

Arguments:

       x: either a two-dimensional contingency table in matrix form, or
          a factor object.

       y: a factor object; ignored if 'x' is a matrix.

zany

谢谢！貌似挺简单的呢