library(dplyr)
## Warning: 패키지 'dplyr'는 R 버전 4.3.2에서 작성되었습니다
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
## Warning: 패키지 'ggplot2'는 R 버전 4.3.2에서 작성되었습니다
data("diamonds")
R.version
## _
## platform x86_64-w64-mingw32
## arch x86_64
## os mingw32
## crt ucrt
## system x86_64, mingw32
## status
## major 4
## minor 3.1
## year 2023
## month 06
## day 16
## svn rev 84548
## language R
## version.string R version 4.3.1 (2023-06-16 ucrt)
## nickname Beagle Scouts
library(dplyr)
getwd()
## [1] "C:/Users/USER/Documents"
Data1<-read.delim("c:/data/Data1.txt")
nrow(Data1)
## [1] 1925
summary(Data1)
## Q1 Q2 Q3 Q4
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:2.000
## Median :4.000 Median :3.000 Median :3.000 Median :3.000
## Mean :3.536 Mean :3.291 Mean :2.928 Mean :3.061
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q5 Q6 Q7 Q8
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :3.000 Median :3.000
## Mean :3.041 Mean :2.796 Mean :3.086 Mean :3.049
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q9 Q10 Q11 Q12 Q13
## Min. :1.000 Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.00 1st Qu.:3.000 1st Qu.:3.000
## Median :3.000 Median :3.000 Median :4.00 Median :4.000 Median :4.000
## Mean :3.066 Mean :2.883 Mean :3.47 Mean :3.421 Mean :3.588
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.000 Max. :5.000
## Q14 Q15 Q16 Q17
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.716 Mean :3.542 Mean :3.791 Mean :3.516
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q18 Q19 Q20 Gender
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :0.0000
## 1st Qu.:4.000 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:0.0000
## Median :4.000 Median :3.000 Median :3.000 Median :0.0000
## Mean :3.804 Mean :3.364 Mean :3.349 Mean :0.4099
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:1.0000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :1.0000
## EDU BF BM Happiness
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.400
## 1st Qu.:2.000 1st Qu.:2.600 1st Qu.:2.400 1st Qu.:3.000
## Median :3.000 Median :3.200 Median :3.000 Median :3.600
## Mean :2.616 Mean :3.172 Mean :2.976 Mean :3.547
## 3rd Qu.:3.000 3rd Qu.:3.800 3rd Qu.:3.600 3rd Qu.:4.000
## Max. :4.000 Max. :5.000 Max. :5.000 Max. :5.000
## Peace
## Min. :1.200
## 1st Qu.:3.200
## Median :3.600
## Mean :3.564
## 3rd Qu.:4.000
## Max. :5.000
library(psych)
## Warning: 패키지 'psych'는 R 버전 4.3.2에서 작성되었습니다
##
## 다음의 패키지를 부착합니다: 'psych'
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
describe(Data1)
## vars n mean sd median trimmed mad min max range skew kurtosis
## Q1 1 1925 3.54 0.94 4.0 3.58 0.00 1.0 5 4.0 -0.75 -0.04
## Q2 2 1925 3.29 0.94 3.0 3.32 1.48 1.0 5 4.0 -0.36 -0.57
## Q3 3 1925 2.93 1.02 3.0 2.93 1.48 1.0 5 4.0 0.06 -1.10
## Q4 4 1925 3.06 0.97 3.0 3.07 1.48 1.0 5 4.0 -0.11 -1.08
## Q5 5 1925 3.04 1.02 3.0 3.05 1.48 1.0 5 4.0 -0.06 -1.09
## Q6 6 1925 2.80 1.12 3.0 2.82 1.48 1.0 5 4.0 0.12 -1.16
## Q7 7 1925 3.09 1.09 3.0 3.10 1.48 1.0 5 4.0 -0.14 -1.11
## Q8 8 1925 3.05 1.09 3.0 3.08 1.48 1.0 5 4.0 -0.15 -1.18
## Q9 9 1925 3.07 1.14 3.0 3.10 1.48 1.0 5 4.0 -0.17 -1.21
## Q10 10 1925 2.88 0.94 3.0 2.87 1.48 1.0 5 4.0 0.15 -0.64
## Q11 11 1925 3.47 0.96 4.0 3.52 1.48 1.0 5 4.0 -0.67 0.05
## Q12 12 1925 3.42 0.99 4.0 3.43 1.48 1.0 5 4.0 -0.43 -0.64
## Q13 13 1925 3.59 0.89 4.0 3.62 0.00 1.0 5 4.0 -0.65 -0.15
## Q14 14 1925 3.72 0.89 4.0 3.78 0.00 1.0 5 4.0 -0.77 0.19
## Q15 15 1925 3.54 0.93 4.0 3.57 1.48 1.0 5 4.0 -0.48 -0.26
## Q16 16 1925 3.79 0.83 4.0 3.87 0.00 1.0 5 4.0 -0.87 0.84
## Q17 17 1925 3.52 1.00 4.0 3.55 0.00 1.0 5 4.0 -0.57 -0.50
## Q18 18 1925 3.80 0.95 4.0 3.91 0.00 1.0 5 4.0 -1.01 0.79
## Q19 19 1925 3.36 0.91 3.0 3.38 1.48 1.0 5 4.0 -0.28 -0.48
## Q20 20 1925 3.35 0.93 3.0 3.36 1.48 1.0 5 4.0 -0.27 -0.68
## Gender 21 1925 0.41 0.49 0.0 0.39 0.00 0.0 1 1.0 0.37 -1.87
## EDU 22 1925 2.62 0.83 3.0 2.64 0.00 1.0 4 3.0 -0.47 -0.34
## BF 23 1925 3.17 0.74 3.2 3.19 0.89 1.0 5 4.0 -0.12 -0.52
## BM 24 1925 2.98 0.78 3.0 2.98 0.89 1.0 5 4.0 0.02 -0.41
## Happiness 25 1925 3.55 0.75 3.6 3.57 0.59 1.4 5 3.6 -0.37 -0.20
## Peace 26 1925 3.56 0.66 3.6 3.59 0.59 1.2 5 3.8 -0.46 0.14
## se
## Q1 0.02
## Q2 0.02
## Q3 0.02
## Q4 0.02
## Q5 0.02
## Q6 0.03
## Q7 0.02
## Q8 0.02
## Q9 0.03
## Q10 0.02
## Q11 0.02
## Q12 0.02
## Q13 0.02
## Q14 0.02
## Q15 0.02
## Q16 0.02
## Q17 0.02
## Q18 0.02
## Q19 0.02
## Q20 0.02
## Gender 0.01
## EDU 0.02
## BF 0.02
## BM 0.02
## Happiness 0.02
## Peace 0.01
glimpse(Data1)
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
t.test(Data1$Happiness)
##
## One Sample t-test
##
## data: Data1$Happiness
## t = 208.06, df = 1924, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 3.513629 3.580501
## sample estimates:
## mean of x
## 3.547065
t.test(Data1$Happiness, mu=3.5)
##
## One Sample t-test
##
## data: Data1$Happiness
## t = 2.7606, df = 1924, p-value = 0.005824
## alternative hypothesis: true mean is not equal to 3.5
## 95 percent confidence interval:
## 3.513629 3.580501
## sample estimates:
## mean of x
## 3.547065
t.test(extra~group, data = sleep)
##
## Welch Two Sample t-test
##
## data: extra by group
## t = -1.8608, df = 17.776, p-value = 0.07939
## alternative hypothesis: true difference in means between group 1 and group 2 is not equal to 0
## 95 percent confidence interval:
## -3.3654832 0.2054832
## sample estimates:
## mean in group 1 mean in group 2
## 0.75 2.33
t.test(Data1$Happiness, Data1$Peace, paired=TRUE)
##
## Paired t-test
##
## data: Data1$Happiness and Data1$Peace
## t = -1.1468, df = 1924, p-value = 0.2516
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -0.04660127 0.01221166
## sample estimates:
## mean difference
## -0.01719481
t.test(Data1$BF, Data1$BM, paired=TRUE)
##
## Paired t-test
##
## data: Data1$BF and Data1$BM
## t = 13.293, df = 1924, p-value < 2.2e-16
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## 0.1669057 0.2246787
## sample estimates:
## mean difference
## 0.1957922
var.test(Data1$Happiness~Data1$Gender)
##
## F test to compare two variances
##
## data: Data1$Happiness by Data1$Gender
## F = 0.96433, num df = 1135, denom df = 788, p-value = 0.5766
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.8473093 1.0958434
## sample estimates:
## ratio of variances
## 0.9643256
t.test(Data1$Happiness~Data1$Gender,var.equal=TRUE)
##
## Two Sample t-test
##
## data: Data1$Happiness by Data1$Gender
## t = 1.3282, df = 1923, p-value = 0.1843
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.02193698 0.11400596
## sample estimates:
## mean in group 0 mean in group 1
## 3.565933 3.519899
var.test(Data1$Peace~Data1$Gender)
##
## F test to compare two variances
##
## data: Data1$Peace by Data1$Gender
## F = 0.75048, num df = 1135, denom df = 788, p-value = 1.03e-05
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.6594103 0.8528296
## sample estimates:
## ratio of variances
## 0.7504771
var.test(Data1$BF~Data1$Gender)
##
## F test to compare two variances
##
## data: Data1$BF by Data1$Gender
## F = 0.86203, num df = 1135, denom df = 788, p-value = 0.02282
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.7574265 0.9795960
## sample estimates:
## ratio of variances
## 0.8620296
var.test(Data1$BM~Data1$Gender)
##
## F test to compare two variances
##
## data: Data1$BM by Data1$Gender
## F = 0.92878, num df = 1135, denom df = 788, p-value = 0.2573
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.8160764 1.0554492
## sample estimates:
## ratio of variances
## 0.9287792
t.test(Data1$Peace~Data1$Gender, var.equal=FALSE)
##
## Welch Two Sample t-test
##
## data: Data1$Peace by Data1$Gender
## t = 2.5335, df = 1534.2, p-value = 0.01139
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 0.01784323 0.14023215
## sample estimates:
## mean in group 0 mean in group 1
## 3.596655 3.517617
t.test(Data1$BF~Data1$Gender, var.equal=FALSE)
##
## Welch Two Sample t-test
##
## data: Data1$BF by Data1$Gender
## t = -3.2543, df = 1612.7, p-value = 0.00116
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.1818157 -0.0450678
## sample estimates:
## mean in group 0 mean in group 1
## 3.125088 3.238530
t.test(Data1$BM~Data1$Gender, var.equal=FALSE)
##
## Welch Two Sample t-test
##
## data: Data1$BM by Data1$Gender
## t = -2.0153, df = 1654.5, p-value = 0.04403
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.144089643 -0.001954333
## sample estimates:
## mean in group 0 mean in group 1
## 2.945863 3.018885
t.test(Data1$BM~Data1$Gender, var.equal=TRUE)
##
## Two Sample t-test
##
## data: Data1$BM by Data1$Gender
## t = -2.0288, df = 1923, p-value = 0.04262
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.143610710 -0.002433266
## sample estimates:
## mean in group 0 mean in group 1
## 2.945863 3.018885
wilcox.test(Data1$Happiness, mu=3.5)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Data1$Happiness
## V = 1029154, p-value = 2.782e-06
## alternative hypothesis: true location is not equal to 3.5
par(mfrow=c(1,2))
hist(Data1$Happiness)
boxplot(Data1$Happiness)
wilcox.test(Data1$Happiness-Data1$Peace, data=Data1)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Data1$Happiness - Data1$Peace
## V = 596154, p-value = 0.3322
## alternative hypothesis: true location is not equal to 0
wilcox.test(Data1$Peace~Data1$Gender, data=Data1)
##
## Wilcoxon rank sum test with continuity correction
##
## data: Data1$Peace by Data1$Gender
## W = 473455, p-value = 0.03373
## alternative hypothesis: true location shift is not equal to 0
wilcox.test(Data1$BM~Data1$Gender, data=Data1)
##
## Wilcoxon rank sum test with continuity correction
##
## data: Data1$BM by Data1$Gender
## W = 425755, p-value = 0.06109
## alternative hypothesis: true location shift is not equal to 0
wilcox.test(Data1$BF~Data1$Gender, data=Data1)
##
## Wilcoxon rank sum test with continuity correction
##
## data: Data1$BF by Data1$Gender
## W = 403502, p-value = 0.0001866
## alternative hypothesis: true location shift is not equal to 0