t.test()的使用中～和，的区别

> y <-1:10
> x <- rep(letters[1:2],5)
> t.test(y~x)
 Welch Two Sample t-test
data:  y by a
t = -0.5, df = 8, p-value = 0.6305
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -5.612008  3.612008
sample estimates:
mean in group a mean in group b 
              5               6

～是讲y和x关联起来了，x="a"的时候y可以为[1,3,5,7,9]，所以"a"的均值为5，为“b”的可以为[2,4,6,8,10]。这时候用‘，’就会报错，因为x不是数，不能直接得到统计量。

> y <-1:10
> x <- rep(letters[1:2],5)
> t.test(y,x)
Error in if (stderr < 10 * .Machine$double.eps * max(abs(mx), abs(my))) stop("data are essentially constant") : 
  missing value where TRUE/FALSE needed
In addition: Warning messages:
1: In mean.default(y) : argument is not numeric or logical: returning NA
2: In var(y) : NAs introduced by coercion

对于x,y为分别的两组数的时候，判断他们之间分布是不是一致，就不能用～。使用～这种关联结构，t.test只能判断x只能为两个值的情况。

> x <- c(rnorm(10))
> y<- c(rnorm(10))
> t.test(x~y)
Error in t.test.formula(x ~ y) : 
  grouping factor must have exactly 2 levels

这种情况应该用"，"。

> x <- c(rnorm(10))
> y<- c(rnorm(10))
> t.test(y,x)

    Welch Two Sample t-test

data:  y and x
t = -0.053873, df = 17.045, p-value = 0.9577
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.9223157  0.8763781
sample estimates:
 mean of x  mean of y 
-0.2160393 -0.1930705

在plot()的时候：

plot(y~x)
plot(y,x)

前者，～左边为因变量，后者“,”后面为因变量。