R自身包含var.test和bartlett.test方差齐性检验，分别对应两组和多组数据。在car包中有levene.test（也是SPSS的默认方差齐性检验方法）。对同一组数据，var.test和bartlett.test检验p值接近，而与levene.test相差甚远。数据是用的Robert A. Muenchen的“R for SAS and SPSS users(2nd edit.)”的mydata100
这个问题我直接发邮件问Robert A. Muenchen，他回复说暂时也想不起来问题出在哪里，但如果有时间会帮忙查查资料找找原因。

请教论坛的朋友们，有知道问题出在哪里的吗？谢谢！


结果如下所示:
> var.test(formula = posttest~gender,data = mydata100)

F test to compare two variances

data:posttest by gender
F = 0.7279, num df = 46, denom df = 51, p-value = 0.2763
alternative hypothesis: true ratio of variances is not equal to 1
95 percent confidence interval:
0.4132401 1.2929517
sample estimates:
ratio of variances
0.7278693

> bartlett.test(formula = posttest~gender,data = mydata100)

Bartlett test of homogeneity of variances

data:posttest by gender
Bartlett's K-squared = 1.196, df = 1, p-value = 0.2741

> library(car)
> leveneTest(y = mydata100$posttest,group = mydata100$gender)
Levene's Test for Homogeneity of Variance (center = median)
Df F value Pr(>F)
group10.4308 0.5131
97