[R 통계분석] 독립표본 t 검정 | 이분산 가정

[R 통계분석] 독립표본 t 검정 | 이분산 가정

#1. 방법

t.test(x, y = NULL,
       alternative = c("two.sided", "less", "greater"),
       mu = 0, paired = FALSE, var.equal = FALSE,
       conf.level = 0.95, ...)

▶ x,y 자리에 데이터 입력함.

▶ var.equal=FALSE 가 디폴트 값, 이분산 가정 t검정을 수행.

▶ 이분산가정 t검정을 Welch's t-test라고 부름.

#2. 예제

> 코드

#데이터 생성
set.seed(1)
height_male=rnorm(50,175,5)
height_female=rnorm(50,165,5)

#t검정 수행
#귀무가설 : height_male = height_female
t.test(height_male, height_female)

#귀무가설 : height_male < height_female
t.test(height_male, height_female, alternative="greater")

#귀무가설 : height_male > height_female
t.test(height_male, height_female, alternative="less")

> 실행결과

> t.test(height_male,height_female)

    Welch Two Sample t-test

data:  height_male and height_female
t = 10.984, df = 95.793, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  8.123654 11.707564
sample estimates:
mean of x mean of y
 175.5022  165.5866

> t.test(height_male,height_female,alternative="greater")

    Welch Two Sample t-test

data:  height_male and height_female
t = 10.984, df = 95.793, p-value < 2.2e-16
alternative hypothesis: true difference in means is greater than 0
95 percent confidence interval:
 8.41625     Inf
sample estimates:
mean of x mean of y
 175.5022  165.5866

> t.test(height_male,height_female,alternative="less")

    Welch Two Sample t-test

data:  height_male and height_female
t = 10.984, df = 95.793, p-value = 1
alternative hypothesis: true difference in means is less than 0
95 percent confidence interval:
     -Inf 11.41497
sample estimates:
mean of x mean of y
 175.5022  165.5866