配对卡方检验

yewuti

> paired <- as.table(matrix(c(157,24,69,18),nrow = 2,dimnames = list(case=c('A','B'),control=c('A','B'))))
> paired
    control
case   A   B
   A 157  69
   B  24  18

各位朋友，像这样一个配对的卡方四个表，如何进行卡方检验呢，还有OR值如何得到呢？虽然数据很简单，可以手动计算。

cosyong

Ref 《统计建模与Ｒ软件》[薛毅、陈萍] chapter 5<若干重要的非参数检验>

> x <- as.table(matrix(c(157,24,69,18),nrow = 2,dimnames = list(case=c('A','B'),control=c('A','B'))))
> x
    control
case   A   B
   A 157  69
   B  24  18
> chisq.test(x)

        Pearson's Chi-squared test with Yates' continuity correction

data:  x
X-squared = 1.9244, df = 1, p-value = 0.1654
# 另外
> fisher.test(x)

        Fisher's Exact Test for Count Data

data:  x
p-value = 0.1504
alternative hypothesis: true odds ratio is not equal to 1
95 percent confidence interval:
 0.8141327 3.5153422
sample estimates:
odds ratio 
  1.702999

OR=1.702999

OR还有三个包可以计算(你自己去check)
1、http://www.inside-r.org/packages/cran/abd/docs/odds.ratio
2、http://minato.sip21c.org/msb/man/oddsratio.html
3、http://artax.karlin.mff.cuni.cz/r-help/library/bstats/html/oddsratio.html

也可以手工计算
1、http://a-little-book-of-r-for-biomedical-statistics.readthedocs.org/en/latest/src/biomedicalstats.html

2、http://www.r-bloggers.com/computing-odds-ratios-in-r/