独立性检验和相关性度量

数据仍然使用了上一节的数据，对数据进行了独立性检验测试，包括了卡方独立性检验、FisherJ精确检验和Cochran-Mantel-Haenszel检验，并计算了phi系数、列联系数和Cramer’s V系数。

> #卡方独立性检验
> library(vcd)

> mytable <- xtabs(~Treatment+Improved,data = Arthritis)

> #治疗情况和改善情况不独立
> chisq.test(mytable)

	Pearson's Chi-squared test

data:  mytable
X-squared = 13.055, df = 2, p-value = 0.001463


> mytable1 <- xtabs(~Improved+Sex,data = Arthritis)

> #性别和改善情况独立
> chisq.test(mytable1)

	Pearson's Chi-squared test

data:  mytable1
X-squared = 4.8407, df = 2, p-value = 0.08889


> #Fisher精确检验
> 
> mytable2 <- xtabs(~Treatment+Improved,data = Arthritis)

> #原假设是：边界固定的列联表中行和列是相互独立的
> fisher.test(mytable2)

	Fisher's Exact Test for Count Data

data:  mytable2
p-value = 0.001393
alternative hypothesis: two.sided


> #Cochran-Mantel-Haenszel检验
> 
> mytable3 <- xtabs(~Treatment+Improved+Sex,data = Arthritis)

> #患者的治疗与得到的改善在性别的每一水平下不独立
> mantelhaen.test(mytable3)

	Cochran-Mantel-Haenszel test

data:  mytable3
Cochran-Mantel-Haenszel M^2 = 14.632, df = 2, p-value = 0.0006647


> #相关性度量
> mytable4 <- xtabs(~Treatment+Improved,data = Arthritis)

> assocstats(mytable4)
                    X^2 df  P(> X^2)
Likelihood Ratio 13.530  2 0.0011536
Pearson          13.055  2 0.0014626

Phi-Coefficient   : NA 
Contingency Coeff.: 0.367 
Cramer's V        : 0.394 
Warning message:
In chisq.test(mytable1) : Chi-squared approximation may be incorrect