臨床統計もおもしろいですよ、その3

64 ：卵の名無しさん：2020/03/16(月) 23:35:45.65 ID:5fhQT99v.net

>>63
PCRの方は中央値だけでデータがないので統計処理は辿れないが、比率の方が計算できる。

> round(35*0.9143)
[1] 32
> round(45*0.6222)
[1] 28
>
> library(fmsb)
> (mat=cbind(c(32,28),c(35,45)-c(32,28)))
[,1] [,2]
[1,] 32 3
[2,] 28 17
> chisq.test(mat)

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

data: mat
X-squared = 7.4667, df = 1, p-value = 0.006285

> fisher.test(mat)

Fisher's Exact Test for Count Data

data: mat
p-value = 0.003669
alternative hypothesis: true odds ratio is not equal to 1
95 percent confidence interval:
1.59236 37.25281
sample estimates:
odds ratio
6.33637