df<-read.delim("c:\\R\\Data\\data1.txt")
dim(df)
## [1] 1925 26
head(df);tail(df)
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20 Gender
## 1 4 4 2 3 4 2 2 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## 2 4 4 4 4 4 3 2 4 4 4 4 4 4 4 4 4 3 4 2 1 0
## 3 4 4 4 4 2 4 4 4 4 2 4 4 4 4 3 4 4 4 4 3 0
## 4 5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## 5 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4 0
## 6 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## EDU BF BM Happiness Peace
## 1 1 3.4 3.2 4.0 4.0
## 2 1 4.0 3.4 4.0 2.8
## 3 2 3.6 3.6 3.8 3.8
## 4 1 4.2 4.0 4.0 4.0
## 5 2 4.0 3.6 4.0 4.0
## 6 1 4.0 4.0 4.0 4.0
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20
## 1920 4 4 3 4 4 2 2 3 4 2 2 4 3 4 4 3 4 4 3 4
## 1921 2 2 2 1 2 2 2 2 2 2 1 3 2 1 3 2 2 2 2 2
## 1922 3 2 2 2 3 1 1 1 1 1 3 3 3 4 4 4 4 5 2 2
## 1923 5 4 4 4 4 2 2 2 2 3 3 4 3 4 3 3 3 4 4 4
## 1924 4 4 4 2 2 4 2 4 4 3 3 2 3 4 3 4 4 4 3 4
## 1925 3 3 1 1 2 1 1 1 1 1 4 4 3 2 2 3 4 4 3 2
## Gender EDU BF BM Happiness Peace
## 1920 1 3 3.8 2.6 3.4 3.6
## 1921 1 2 1.8 2.0 2.0 2.0
## 1922 0 2 2.4 1.0 3.4 3.4
## 1923 0 2 4.2 2.2 3.4 3.6
## 1924 1 2 3.2 3.4 3.0 3.8
## 1925 0 3 2.0 1.0 3.0 3.2
str(df)
## 'data.frame': 1925 obs. of 26 variables:
## $ Q1 : int 4 4 4 5 4 4 4 4 4 4 ...
## $ Q2 : int 4 4 4 4 4 4 2 2 4 4 ...
## $ Q3 : int 2 4 4 4 4 4 4 4 4 2 ...
## $ Q4 : int 3 4 4 4 4 4 4 4 4 2 ...
## $ Q5 : int 4 4 2 4 4 4 4 4 2 4 ...
## $ Q6 : int 2 3 4 4 4 4 4 4 1 2 ...
## $ Q7 : int 2 2 4 4 4 4 4 4 3 4 ...
## $ Q8 : int 4 4 4 4 4 4 5 5 2 2 ...
## $ Q9 : int 4 4 4 4 2 4 5 5 3 4 ...
## $ Q10 : int 4 4 2 4 4 4 5 5 2 4 ...
## $ Q11 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q12 : int 4 4 4 4 4 4 5 5 3 4 ...
## $ Q13 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q14 : int 4 4 4 4 4 4 5 5 5 4 ...
## $ Q15 : int 4 4 3 4 4 4 4 2 3 4 ...
## $ Q16 : int 4 4 4 4 4 4 5 2 4 4 ...
## $ Q17 : int 4 3 4 4 4 4 2 2 4 4 ...
## $ Q18 : int 4 4 4 4 4 4 4 4 4 4 ...
## $ Q19 : int 4 2 4 4 4 4 4 2 4 2 ...
## $ Q20 : int 4 1 3 4 4 4 4 2 4 2 ...
## $ Gender : int 0 0 0 0 0 0 0 0 1 0 ...
## $ EDU : int 1 1 2 1 2 1 1 1 4 3 ...
## $ BF : num 3.4 4 3.6 4.2 4 4 3.6 3.6 3.6 3.2 ...
## $ BM : num 3.2 3.4 3.6 4 3.6 4 4.6 4.6 2.2 3.2 ...
## $ Happiness: num 4 4 3.8 4 4 4 4.8 4.4 3.8 4 ...
## $ Peace : num 4 2.8 3.8 4 4 4 3.8 2.4 4 3.2 ...
summary(df)
## 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
df1<-df[,c(21:26)]
summary(df1)
## Gender EDU BF BM
## Min. :0.0000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:2.000 1st Qu.:2.600 1st Qu.:2.400
## Median :0.0000 Median :3.000 Median :3.200 Median :3.000
## Mean :0.4099 Mean :2.616 Mean :3.172 Mean :2.976
## 3rd Qu.:1.0000 3rd Qu.:3.000 3rd Qu.:3.800 3rd Qu.:3.600
## Max. :1.0000 Max. :4.000 Max. :5.000 Max. :5.000
## Happiness Peace
## Min. :1.400 Min. :1.200
## 1st Qu.:3.000 1st Qu.:3.200
## Median :3.600 Median :3.600
## Mean :3.547 Mean :3.564
## 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000
attach(df1)
mean(Happiness)
## [1] 3.547065
t.test(Happiness, Peace, paired = TRUE)
##
## Paired t-test
##
## data: Happiness and Peace
## t = -1.1468, df = 1924, p-value = 0.2516
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.04660127 0.01221166
## sample estimates:
## mean of the differences
## -0.01719481
wilcox.test(Happiness, mu=3.5)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Happiness
## V = 1029154, p-value = 2.782e-06
## alternative hypothesis: true location is not equal to 3.5
options(scipen=999)
wilcox.test(Happiness-Peace)
##
## Wilcoxon signed rank test with continuity correction
##
## data: Happiness - Peace
## V = 596154, p-value = 0.3322
## alternative hypothesis: true location is not equal to 0
library(ggplot2)
library(gapminder)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1
## v purrr 0.3.4
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(ggplot2)
ggplot(gapminder, aes(x=gdpPercap, y=lifeExp, col=continent))+geom_point() + scale_x_log10()
ggplot(gapminder, aes(x=gdpPercap, y=lifeExp, col=continent, size=pop))+geom_point() + scale_x_log10()
ggplot(gapminder, aes(x=gdpPercap, y=lifeExp, col=continent, size=pop))+geom_point(alpha=0.5) + scale_x_log10()
ggplot(gapminder, aes(x=gdpPercap, y=lifeExp, col=continent, size=pop))+geom_point(alpha=0.5) + scale_x_log10() + facet_wrap(~year)
