library(dplyr)
library(ggplot2)
library(tidyverse)
library(psych)
library(magrittr)
library(knitr)
library(kableExtra)
library(readr)
politics_media <- read_csv("~/2nd round of hell/politics_media.csv")
politics = politics_media %>%
select(lrscale, stflife, polintr, stfdem, stfgov, trstprl, trstplt, trstprt, cptppola, trstep, trstun, stfeco, stfhlth, stfedu, stflife)
politics %>%
filter(lrscale != 77) %>%
filter(lrscale != 88) %>%
filter(lrscale != 99 )
## # A tibble: 2,276 x 14
## lrscale stflife polintr stfdem stfgov trstprl trstplt trstprt cptppola
## <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 6 4 3 7 5 4 5 6 3
## 2 7 6 3 7 5 7 7 3 4
## 3 5 6 2 7 6 7 2 0 3
## 4 6 4 3 6 5 7 5 6 2
## 5 5 6 3 7 6 6 6 7 3
## 6 7 5 3 6 6 6 6 3 2
## 7 6 7 2 6 7 5 7 7 2
## 8 8 5 3 5 6 5 7 3 3
## 9 7 7 2 8 7 6 7 5 3
## 10 8 6 2 5 6 5 3 2 4
## # … with 2,266 more rows, and 5 more variables: trstep <int>,
## # trstun <int>, stfeco <int>, stfhlth <int>, stfedu <int>
politics %>%
filter(stflife != 77) %>%
filter(stflife != 88) %>%
filter(stflife != 99)
## # A tibble: 2,752 x 14
## lrscale stflife polintr stfdem stfgov trstprl trstplt trstprt cptppola
## <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 6 4 3 7 5 4 5 6 3
## 2 7 6 3 7 5 7 7 3 4
## 3 5 6 2 7 6 7 2 0 3
## 4 6 4 3 6 5 7 5 6 2
## 5 5 6 3 7 6 6 6 7 3
## 6 7 5 3 6 6 6 6 3 2
## 7 6 7 2 6 7 5 7 7 2
## 8 88 4 4 7 6 2 3 3 2
## 9 8 5 3 5 6 5 7 3 3
## 10 7 7 2 8 7 6 7 5 3
## # … with 2,742 more rows, and 5 more variables: trstep <int>,
## # trstun <int>, stfeco <int>, stfhlth <int>, stfedu <int>
politics.1 = politics %>%
select(lrscale, stflife, polintr, stfdem, stfgov, trstprl, trstplt, trstprt, cptppola, trstep, trstun, stfeco, stfhlth, stfedu, stflife)
politics.1 %>%
filter(polintr != 7) %>%
filter(polintr != 8) %>%
filter(polintr != 9 )
## # A tibble: 2,754 x 14
## lrscale stflife polintr stfdem stfgov trstprl trstplt trstprt cptppola
## <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 6 4 3 7 5 4 5 6 3
## 2 7 6 3 7 5 7 7 3 4
## 3 5 6 2 7 6 7 2 0 3
## 4 6 4 3 6 5 7 5 6 2
## 5 5 6 3 7 6 6 6 7 3
## 6 7 5 3 6 6 6 6 3 2
## 7 6 7 2 6 7 5 7 7 2
## 8 88 4 4 7 6 2 3 3 2
## 9 8 5 3 5 6 5 7 3 3
## 10 7 7 2 8 7 6 7 5 3
## # … with 2,744 more rows, and 5 more variables: trstep <int>,
## # trstun <int>, stfeco <int>, stfhlth <int>, stfedu <int>
politics.1 %>%
filter(stfedu != 77) %>%
filter(stfedu != 88) %>%
filter(stfedu != 99)
## # A tibble: 2,669 x 14
## lrscale stflife polintr stfdem stfgov trstprl trstplt trstprt cptppola
## <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 6 4 3 7 5 4 5 6 3
## 2 7 6 3 7 5 7 7 3 4
## 3 5 6 2 7 6 7 2 0 3
## 4 6 4 3 6 5 7 5 6 2
## 5 5 6 3 7 6 6 6 7 3
## 6 7 5 3 6 6 6 6 3 2
## 7 6 7 2 6 7 5 7 7 2
## 8 88 4 4 7 6 2 3 3 2
## 9 8 5 3 5 6 5 7 3 3
## 10 7 7 2 8 7 6 7 5 3
## # … with 2,659 more rows, and 5 more variables: trstep <int>,
## # trstun <int>, stfeco <int>, stfhlth <int>, stfedu <int>
politics.1 %>%
filter(cptppola != 7) %>%
filter(cptppola != 8) %>%
filter(cptppola!= 9 )
## # A tibble: 2,731 x 14
## lrscale stflife polintr stfdem stfgov trstprl trstplt trstprt cptppola
## <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 6 4 3 7 5 4 5 6 3
## 2 7 6 3 7 5 7 7 3 4
## 3 5 6 2 7 6 7 2 0 3
## 4 6 4 3 6 5 7 5 6 2
## 5 5 6 3 7 6 6 6 7 3
## 6 7 5 3 6 6 6 6 3 2
## 7 6 7 2 6 7 5 7 7 2
## 8 88 4 4 7 6 2 3 3 2
## 9 8 5 3 5 6 5 7 3 3
## 10 7 7 2 8 7 6 7 5 3
## # … with 2,721 more rows, and 5 more variables: trstep <int>,
## # trstun <int>, stfeco <int>, stfhlth <int>, stfedu <int>
polintr - How interested in politics: factor
stfdem - How satisfied with the way democracy works in country: from 0 to 10
politics.1 = politics %>%
select(polintr, stflife)
politics.1$polintr <- ifelse (politics.1$polintr == 1, "Very interested",
ifelse(politics.1$polintr == 2, "Quite interested",
ifelse(politics.1$polintr == 3, "Hardly interested", "Not interested")))
politics.1$trstprt <- as.numeric(as.character(politics.1$stflife))
politics.1$polintr <- as.factor(politics.1$polintr)
politics.2 <- data.frame(politics.1$polintr,politics.1$stflife)
str(politics.2)
## 'data.frame': 2757 obs. of 2 variables:
## $ politics.1.polintr: Factor w/ 4 levels "Hardly interested",..: 1 1 3 1 1 1 3 2 1 3 ...
## $ politics.1.stflife: int 4 6 6 4 6 5 7 4 5 7 ...
politics.11 = politics.1 %>%
filter(politics.1$stflife != 88)
politics.11 = politics.11 %>%
filter(politics.11$stflife != 77)
politics.11 = politics.11 %>%
filter(politics.11$stflife != 99)
describeBy(politics.11$stflife, politics.11$polintr, mat = TRUE) %>% #create dataframe
select(polintr = group1, N=n, Mean=mean, SD=sd, Median=median, Min=min, Max=max,
Skew=skew, Kurtosis=kurtosis, st.error = se) %>%
kable(align=c("lrrrrrrrr"), digits=2, row.names = FALSE,
caption="Satisfaction with democracy by political preferences") %>%
kable_styling(bootstrap_options=c("bordered", "responsive","striped"), full_width = FALSE)
Satisfaction with democracy by political preferences
|
polintr
|
N
|
Mean
|
SD
|
Median
|
Min
|
Max
|
Skew
|
Kurtosis
|
st.error
|
|
Hardly interested
|
733
|
7.23
|
1.90
|
8
|
0
|
10
|
-0.97
|
1.42
|
0.07
|
|
Not interested
|
747
|
7.11
|
2.00
|
7
|
0
|
10
|
-0.86
|
1.02
|
0.07
|
|
Quite interested
|
964
|
7.29
|
1.80
|
7
|
0
|
10
|
-1.02
|
2.00
|
0.06
|
|
Very interested
|
308
|
7.54
|
1.87
|
8
|
0
|
10
|
-0.99
|
1.35
|
0.11
|
par(mar = c(3,10,0,3))
barplot(table(politics.1$polintr)/nrow(politics.1)*100, horiz = T, xlim = c(0,60), las = 2)
ggplot()+
geom_boxplot(data = politics.1, aes(x = polintr, y = stflife)) +
ylim(c(0,10))
## Warning: Removed 5 rows containing non-finite values (stat_boxplot).
library(car)
## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:psych':
##
## logit
## The following object is masked from 'package:purrr':
##
## some
## The following object is masked from 'package:dplyr':
##
## recode
leveneTest(politics.11$stflife ~ politics.11$polintr)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 1.8406 0.1376
## 2748
oneway.test(politics.11$stflife ~ politics.11$polintr, var.equal = T)
##
## One-way analysis of means
##
## data: politics.11$stflife and politics.11$polintr
## F = 3.8929, num df = 3, denom df = 2748, p-value = 0.008659
aov.out <- aov(politics.11$stflife ~ politics.11$polintr) # another function of ANOVA which should be used here
summary(aov.out)
## Df Sum Sq Mean Sq F value Pr(>F)
## politics.11$polintr 3 42 13.893 3.893 0.00866 **
## Residuals 2748 9807 3.569
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova.res <- residuals(object = aov.out)
describe(anova.res)
## vars n mean sd median trimmed mad min max range skew kurtosis
## X1 1 2752 0 1.89 -0.11 0.14 1.48 -7.54 2.89 10.43 -0.96 1.48
## se
## X1 0.04
shapiro.test(x = anova.res)
##
## Shapiro-Wilk normality test
##
## data: anova.res
## W = 0.93479, p-value < 2.2e-16
layout(matrix(1:4, 2, 2))
plot(aov.out)
hist(anova.res)
