250609

# 1. 데이터 로드 (내장 데이터셋)
data(chickwts)
df <- chickwts
head(df)

##   weight      feed
## 1    179 horsebean
## 2    160 horsebean
## 3    136 horsebean
## 4    227 horsebean
## 5    217 horsebean
## 6    168 horsebean

summary(df)

##      weight             feed   
##  Min.   :108.0   casein   :12  
##  1st Qu.:204.5   horsebean:10  
##  Median :258.0   linseed  :12  
##  Mean   :261.3   meatmeal :11  
##  3rd Qu.:323.5   soybean  :14  
##  Max.   :423.0   sunflower:12

# weight : 오른쪽 꼬리분포? 왼쪽 꼬리분포?
# mean>median 성립하면 오른쪽 꼬리분포

# feed  변수 범주형 변수 


# 2. chickwts$weight 벡터 요약
summary(chickwts$weight)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   108.0   204.5   258.0   261.3   323.5   423.0

length(chickwts$weight)  # 관측치 수 확인

## [1] 71

# 3. 일표본 t-검정: 평균이 260인지 검정 (양측 검정)
t.test(chickwts$weight, mu = 260)

## 
##  One Sample t-test
## 
## data:  chickwts$weight
## t = 0.14137, df = 70, p-value = 0.888
## alternative hypothesis: true mean is not equal to 260
## 95 percent confidence interval:
##  242.8301 279.7896
## sample estimates:
## mean of x 
##  261.3099

# mu : 모평균

# 1. 데이터 불러오기
data("PlantGrowth")
# 2. ctrl 그룹 추출
ctrl <- subset(PlantGrowth, group == "ctrl")$weight
# 3. 일표본 t-검정 (mu = 5)
t.test(ctrl, mu = 5)

## 
##  One Sample t-test
## 
## data:  ctrl
## t = 0.17355, df = 9, p-value = 0.8661
## alternative hypothesis: true mean is not equal to 5
## 95 percent confidence interval:
##  4.614882 5.449118
## sample estimates:
## mean of x 
##     5.032

group_ctrl <- subset(PlantGrowth, group == "ctrl")$weight
group_trt1 <- subset(PlantGrowth, group == "trt1")$weight
# 독립표본 t-검정
t.test(group_ctrl, group_trt1, var.equal = TRUE) 

## 
##  Two Sample t-test
## 
## data:  group_ctrl and group_trt1
## t = 1.1913, df = 18, p-value = 0.249
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.2833003  1.0253003
## sample estimates:
## mean of x mean of y 
##     5.032     4.661

# 1. 데이터 불러오기
data(sleep)
# 2. 데이터 구조 확인
str(sleep)

## 'data.frame':    20 obs. of  3 variables:
##  $ extra: num  0.7 -1.6 -0.2 -1.2 -0.1 3.4 3.7 0.8 0 2 ...
##  $ group: Factor w/ 2 levels "1","2": 1 1 1 1 1 1 1 1 1 1 ...
##  $ ID   : Factor w/ 10 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...

# 'data.frame': 20 obs. of  3 variables:
# $ extra : num  0.7 -1.6 -0.2 -1.2 -0.1 3.4 3.7 0.8 0 2 ...
# $ group : Factor w/ 2 levels "1","2": 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2
# $ ID    : int  1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10
# 3. 독립표본 t-검정 수행
t_test_result <- t.test(extra ~ group, data = sleep, var.equal = TRUE)
# 4. 결과 출력
print(t_test_result)

## 
##  Two Sample t-test
## 
## data:  extra by group
## t = -1.8608, df = 18, p-value = 0.07919
## alternative hypothesis: true difference in means between group 1 and group 2 is not equal to 0
## 95 percent confidence interval:
##  -3.363874  0.203874
## sample estimates:
## mean in group 1 mean in group 2 
##            0.75            2.33

data(sleep) 
# sleep 데이터: group 1, group 2 비교
group1 <- subset(sleep, group == 1)$extra
group2 <- subset(sleep, group == 2)$extra

# 대응표본 t-검정 (paired = TRUE)
t.test(group1, group2, paired = TRUE)

## 
##  Paired t-test
## 
## data:  group1 and group2
## t = -4.0621, df = 9, p-value = 0.002833
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
##  -2.4598858 -0.7001142
## sample estimates:
## mean difference 
##           -1.58