rm(list = ls())
# 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
# weight는 오른쪽꼬리분포인지 왼쪽꼬리인지??
# 답 : mean > median이면 오른쪽 꼬리분포
# feed 변수는 범주형 변수인가? 맞습니다.
# chickwts 데이터 관측치 수(표본크기)갯수는? -> 12+10+12+11+14+12
chickwts$weight # -> 값만 출력
## [1] 179 160 136 227 217 168 108 124 143 140 309 229 181 141 260 203 148 169 213
## [20] 257 244 271 243 230 248 327 329 250 193 271 316 267 199 171 158 248 423 340
## [39] 392 339 341 226 320 295 334 322 297 318 325 257 303 315 380 153 263 242 206
## [58] 344 258 368 390 379 260 404 318 352 359 216 222 283 332
# 2. chickwts$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
# 결과 해석
# - 귀무가설(H0): 평균 무게 = 260g
# - 대립가설(H1): 평균 무게 ≠ 260g
# - p-value < 0.05이면 귀무가설 기각 (260과 유의한 차이)
# group 1의 extra 수면 증가량이 평균 1.5와 유의하게
# 다른지 확인하기 위한 양측검정 예시
# 1. sleep 데이터 불러오기
data(sleep)
head(sleep)
## extra group ID
## 1 0.7 1 1
## 2 -1.6 1 2
## 3 -0.2 1 3
## 4 -1.2 1 4
## 5 -0.1 1 5
## 6 3.4 1 6
summary(sleep)
## extra group ID
## Min. :-1.600 1:10 1 :2
## 1st Qu.:-0.025 2:10 2 :2
## Median : 0.950 3 :2
## Mean : 1.540 4 :2
## 3rd Qu.: 3.400 5 :2
## Max. : 5.500 6 :2
## (Other):8
# extra는 mean > median이기 때문에 오른쪽꼬리분포
# group은 범주형 변수
# 데이터 크기는 10+10 = 20
# 2. group 1만 추출
group1 <- subset(sleep, group == 1)$extra
# 3. 단일표본 t-검정 수행 (모평균 1.5와 비교)
t.test(group1, mu = 1.5)
##
## One Sample t-test
##
## data: group1
## t = -1.3257, df = 9, p-value = 0.2176
## alternative hypothesis: true mean is not equal to 1.5
## 95 percent confidence interval:
## -0.5297804 2.0297804
## sample estimates:
## mean of x
## 0.75
# 귀무가설: ctrl 그룹의 평균 무게는 5.0이다.
# 1. 데이터 불러오기
data("PlantGrowth")
head(PlantGrowth)
## weight group
## 1 4.17 ctrl
## 2 5.58 ctrl
## 3 5.18 ctrl
## 4 6.11 ctrl
## 5 4.50 ctrl
## 6 4.61 ctrl
summary(PlantGrowth)
## weight group
## Min. :3.590 ctrl:10
## 1st Qu.:4.550 trt1:10
## Median :5.155 trt2:10
## Mean :5.073
## 3rd Qu.:5.530
## Max. :6.310
# 2. ctrl 그룹 추출
ctrl <- subset(PlantGrowth, group == "ctrl")$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
data("PlantGrowth")
# 대조군 vs 실험군1 비교
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
# 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