자료 읽혀들이기.
red.black<-read.table("red_black.txt", header=TRUE, sep="")
str(red.black)## 'data.frame': 58 obs. of 23 variables:
## $ Color: chr "Curitiba" "Curitiba" "Curitiba" "Curitiba" ...
## $ Q1 : int 3 2 3 4 4 3 3 3 2 1 ...
## $ Q2_1 : int 3 5 4 3 4 3 4 5 5 4 ...
## $ Q2_2 : int 4 5 4 4 5 4 4 5 4 5 ...
## $ Q2_3 : int 3 5 3 2 3 4 3 5 3 4 ...
## $ Q2_4 : int 4 5 4 4 3 4 5 5 5 5 ...
## $ Q2_5 : int 3 5 4 4 5 4 4 5 4 4 ...
## $ Q2_6 : int 3 5 5 4 5 3 5 5 5 4 ...
## $ Q3 : int 3 3 NA 3 5 4 3 4 3 2 ...
## $ Q4_1 : int 4 5 3 5 4 3 4 5 4 3 ...
## $ Q4_2 : int 4 3 4 4 3 3 3 4 2 2 ...
## $ Q4_3 : int 2 4 4 2 3 2 2 5 3 5 ...
## $ Q4_4 : int 2 4 4 3 3 3 2 5 3 4 ...
## $ Q4_5 : int 2 5 3 5 4 4 2 5 3 4 ...
## $ Q4_6 : int 2 2 2 2 3 2 2 5 3 3 ...
## $ Q5_1 : int 1 4 3 5 2 3 2 5 3 2 ...
## $ Q5_2 : int 2 5 4 5 3 3 2 5 3 4 ...
## $ Q5_3 : int 2 4 4 4 4 3 2 5 3 3 ...
## $ Q5_4 : int 3 4 4 5 4 4 3 5 3 5 ...
## $ Q5_5 : int 4 5 4 4 4 4 3 5 3 3 ...
## $ Q6_1 : int 2 2 1 1 2 2 1 2 1 1 ...
## $ Q6_2 : int 1 2 2 1 1 1 1 1 1 2 ...
## $ Q6_4 : int 2 1 3 2 1 3 2 1 2 2 ...head(red.black)## Color Q1 Q2_1 Q2_2 Q2_3 Q2_4 Q2_5 Q2_6 Q3 Q4_1 Q4_2 Q4_3 Q4_4 Q4_5
## 1 Curitiba 3 3 4 3 4 3 3 3 4 4 2 2 2
## 2 Curitiba 2 5 5 5 5 5 5 3 5 3 4 4 5
## 3 Curitiba 3 4 4 3 4 4 5 NA 3 4 4 4 3
## 4 Curitiba 4 3 4 2 4 4 4 3 5 4 2 3 5
## 5 Curitiba 4 4 5 3 3 5 5 5 4 3 3 3 4
## 6 Curitiba 3 3 4 4 4 4 3 4 3 3 2 3 4
## Q4_6 Q5_1 Q5_2 Q5_3 Q5_4 Q5_5 Q6_1 Q6_2 Q6_4
## 1 2 1 2 2 3 4 2 1 2
## 2 2 4 5 4 4 5 2 2 1
## 3 2 3 4 4 4 4 1 2 3
## 4 2 5 5 4 5 4 1 1 2
## 5 3 2 3 4 4 4 2 1 1
## 6 2 3 3 3 4 4 2 1 3Data Cleaning
red.black.2<-red.black
str(red.black.2)## 'data.frame': 58 obs. of 23 variables:
## $ Color: chr "Curitiba" "Curitiba" "Curitiba" "Curitiba" ...
## $ Q1 : int 3 2 3 4 4 3 3 3 2 1 ...
## $ Q2_1 : int 3 5 4 3 4 3 4 5 5 4 ...
## $ Q2_2 : int 4 5 4 4 5 4 4 5 4 5 ...
## $ Q2_3 : int 3 5 3 2 3 4 3 5 3 4 ...
## $ Q2_4 : int 4 5 4 4 3 4 5 5 5 5 ...
## $ Q2_5 : int 3 5 4 4 5 4 4 5 4 4 ...
## $ Q2_6 : int 3 5 5 4 5 3 5 5 5 4 ...
## $ Q3 : int 3 3 NA 3 5 4 3 4 3 2 ...
## $ Q4_1 : int 4 5 3 5 4 3 4 5 4 3 ...
## $ Q4_2 : int 4 3 4 4 3 3 3 4 2 2 ...
## $ Q4_3 : int 2 4 4 2 3 2 2 5 3 5 ...
## $ Q4_4 : int 2 4 4 3 3 3 2 5 3 4 ...
## $ Q4_5 : int 2 5 3 5 4 4 2 5 3 4 ...
## $ Q4_6 : int 2 2 2 2 3 2 2 5 3 3 ...
## $ Q5_1 : int 1 4 3 5 2 3 2 5 3 2 ...
## $ Q5_2 : int 2 5 4 5 3 3 2 5 3 4 ...
## $ Q5_3 : int 2 4 4 4 4 3 2 5 3 3 ...
## $ Q5_4 : int 3 4 4 5 4 4 3 5 3 5 ...
## $ Q5_5 : int 4 5 4 4 4 4 3 5 3 3 ...
## $ Q6_1 : int 2 2 1 1 2 2 1 2 1 1 ...
## $ Q6_2 : int 1 2 2 1 1 1 1 1 1 2 ...
## $ Q6_4 : int 2 1 3 2 1 3 2 1 2 2 ...red.black.2$Color<-factor(red.black.2$Color, levels=c("Curitiba", "Veja"))
red.black.2$Q6_1<-factor(red.black.2$Q6_1, levels=1:2, labels=c("Male", "Female"))
red.black.2$Q6_2<-factor(red.black.2$Q6_2, levels=1:2, labels=c("Glasses", "No.Glasses"))
red.black.2$Q6_4<-factor(red.black.2$Q6_4, levels=1:4, labels=c("Seoul", "Gyunggi", "Kangwon", "Other"))Curitiba 와 Veja 응답 평균값 비교
options(digits=2)
aggregate(red.black.2[,-c(1, 21:23)],by=list(red.black[,1]),mean, na.rm=TRUE)## Group.1 Q1 Q2_1 Q2_2 Q2_3 Q2_4 Q2_5 Q2_6 Q3 Q4_1 Q4_2 Q4_3 Q4_4 Q4_5
## 1 Curitiba 3.1 4.0 4.2 3.8 4.3 4.3 4.2 3.1 4.2 3.2 3.1 3.0 3.3
## 2 Veja 3.4 4.1 3.9 3.7 4.3 4.2 4.1 3.5 3.6 3.0 3.6 3.7 3.5
## Q4_6 Q5_1 Q5_2 Q5_3 Q5_4 Q5_5
## 1 2.8 3.0 3.5 3.4 4.1 4.0
## 2 3.5 3.5 3.8 3.6 4.0 3.721-23번의 응답 테이블
table(red.black.2[,21])##
## Male Female
## 33 25table(red.black.2[,c(1,21)])## Q6_1
## Color Male Female
## Curitiba 16 14
## Veja 17 11table(red.black.2[,c(1,22)])## Q6_2
## Color Glasses No.Glasses
## Curitiba 16 14
## Veja 16 12table(red.black.2[,c(1,23)])## Q6_4
## Color Seoul Gyunggi Kangwon Other
## Curitiba 17 10 2 1
## Veja 9 12 6 1평균 점수에 차이가 있어보이는 Q3, Q4에 대하여 t-test 수행. default로 Welch’s Approxiation 수행
t.test(Q3~Color, data=red.black.2)##
## Welch Two Sample t-test
##
## data: Q3 by Color
## t = -1.6, df = 54, p-value = 0.1205
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.780 0.093
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.1 3.5t.test(Q4_1~Color, data=red.black.2)##
## Welch Two Sample t-test
##
## data: Q4_1 by Color
## t = 2.6, df = 55, p-value = 0.01198
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.13 0.99
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.2 3.6한꺼번에 수행하려면 t.test 의 구조를 이용하여 함수 작성 후 apply() 적용.
t<-function(x) {t.test(x~Color, data=red.black.2, na.rm=TRUE)}
apply(red.black.2[,-c(1,21:23)],2, t)## $Q1
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -1.4, df = 56, p-value = 0.1743
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.71 0.13
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.1 3.4
##
##
## $Q2_1
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -0.59, df = 56, p-value = 0.5604
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.48 0.27
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.0 4.1
##
##
## $Q2_2
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 2.3, df = 55, p-value = 0.02525
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.044 0.637
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.2 3.9
##
##
## $Q2_3
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.47, df = 54, p-value = 0.6426
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.29 0.47
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.8 3.7
##
##
## $Q2_4
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.054, df = 50, p-value = 0.9572
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.43 0.46
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.3 4.3
##
##
## $Q2_5
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.091, df = 53, p-value = 0.9281
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.35 0.39
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.3 4.2
##
##
## $Q2_6
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.12, df = 56, p-value = 0.9071
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.38 0.43
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.2 4.1
##
##
## $Q3
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -1.6, df = 54, p-value = 0.1205
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.780 0.093
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.1 3.5
##
##
## $Q4_1
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 2.6, df = 55, p-value = 0.01198
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.13 0.99
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.2 3.6
##
##
## $Q4_2
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.55, df = 51, p-value = 0.5842
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.35 0.61
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.2 3.0
##
##
## $Q4_3
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -2.1, df = 56, p-value = 0.04423
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.067 -0.014
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.1 3.6
##
##
## $Q4_4
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -2.7, df = 55, p-value = 0.008063
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.11 -0.17
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.0 3.7
##
##
## $Q4_5
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -0.77, df = 51, p-value = 0.4452
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.73 0.33
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.3 3.5
##
##
## $Q4_6
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -2.5, df = 55, p-value = 0.01516
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.20 -0.13
## sample estimates:
## mean in group Curitiba mean in group Veja
## 2.8 3.5
##
##
## $Q5_1
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -1.8, df = 56, p-value = 0.07144
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.120 0.048
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.0 3.5
##
##
## $Q5_2
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -0.85, df = 54, p-value = 0.4016
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.73 0.30
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.5 3.8
##
##
## $Q5_3
##
## Welch Two Sample t-test
##
## data: x by Color
## t = -0.78, df = 56, p-value = 0.4362
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.74 0.33
## sample estimates:
## mean in group Curitiba mean in group Veja
## 3.4 3.6
##
##
## $Q5_4
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 0.3, df = 55, p-value = 0.7651
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.38 0.51
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.1 4.0
##
##
## $Q5_5
##
## Welch Two Sample t-test
##
## data: x by Color
## t = 1.2, df = 53, p-value = 0.2353
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.21 0.85
## sample estimates:
## mean in group Curitiba mean in group Veja
## 4.0 3.7