FIT 3152 Assignment 1
Student ID: 33368066
Set Working Directory
getwd()## [1] "/Users/deslyn/Desktop/Monash/FIT 3152 /Assignment 1"setwd("~/Desktop/Monash/FIT 3152 /Assignment 1")Read The File of The Data
rm(list = ls())
set.seed(33368066) # Your Student Number
VCData = read.csv("WVSExtract.csv")
VC = VCData[sample(1:nrow(VCData),50000, replace=FALSE),]
VC = VC[,c(1:6, sort(sample(7:46,17, replace = FALSE)), 47:53,
sort(sample(54:69,10, replace = FALSE)))]install and use libraries
#install.packages("dplyr")
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union#install.packages("tidyr")
library(tidyr)
#install.packages("ggplot2")
library(ggplot2)
#install.packages("factoextra")
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBaDescribe Overall Data
Show attributes
colnames(VC)## [1] "Country" "TPeople" "TFamily" "TNeighbourhood"
## [5] "TKnow" "TMeet" "VFamily" "VFriends"
## [9] "VLeisure" "VReligion" "HSatFin" "HMedicine"
## [13] "EPrivate" "ECompetition" "EHardWork" "PIAB"
## [17] "STOpportunity" "STFaith" "STImportant" "PNewspaper"
## [21] "PMobile" "PEmail" "PSocial" "PDemImp"
## [25] "PDemCurrent" "PSatisfied" "MF" "Age"
## [29] "Edu" "Employment" "CReligious" "CPress"
## [33] "CTelevision" "CUnions" "CCourts" "CPParties"
## [37] "CParliament" "CCivilService" "CElections" "CEnvOrg"Show number of rows and columns
dim(VC)## [1] 50000 40Show data types
str(VC)## 'data.frame': 50000 obs. of 40 variables:
## $ Country : chr "NLD" "TUN" "PHL" "SGP" ...
## $ TPeople : int 1 2 2 2 1 2 2 2 2 2 ...
## $ TFamily : int 1 3 1 1 1 1 1 1 1 1 ...
## $ TNeighbourhood: int 1 4 2 2 2 2 2 1 3 2 ...
## $ TKnow : int 1 2 1 2 2 2 2 1 2 2 ...
## $ TMeet : int 2 4 3 3 3 2 3 4 4 3 ...
## $ VFamily : int 1 1 1 1 1 1 1 1 1 2 ...
## $ VFriends : int 1 2 1 2 2 2 2 1 2 2 ...
## $ VLeisure : int 1 1 3 2 2 2 2 1 2 2 ...
## $ VReligion : int 4 2 2 2 1 2 3 1 3 1 ...
## $ HSatFin : int 10 10 9 10 7 10 4 7 6 7 ...
## $ HMedicine : int 4 4 3 4 4 4 3 4 4 3 ...
## $ EPrivate : int 7 3 6 6 7 1 5 10 1 2 ...
## $ ECompetition : int 8 1 7 5 8 1 -1 1 1 1 ...
## $ EHardWork : int 7 1 5 6 3 5 3 10 1 8 ...
## $ PIAB : int 4 4 4 2 4 2 3 1 4 4 ...
## $ STOpportunity : int 5 8 7 10 2 10 5 5 10 9 ...
## $ STFaith : int 1 8 6 6 5 4 5 5 4 8 ...
## $ STImportant : int 1 1 4 6 6 2 4 5 3 1 ...
## $ PNewspaper : int 1 5 3 2 4 2 4 3 5 5 ...
## $ PMobile : int 1 5 1 1 1 1 1 3 1 1 ...
## $ PEmail : int 1 5 2 2 2 5 4 5 1 5 ...
## $ PSocial : int 3 1 1 1 1 1 1 1 1 5 ...
## $ PDemImp : int 10 10 7 10 8 10 9 10 8 10 ...
## $ PDemCurrent : int 7 4 7 10 8 9 5 10 5 3 ...
## $ PSatisfied : int 6 5 8 7 8 8 5 5 3 3 ...
## $ MF : int 2 2 2 2 2 2 2 1 2 2 ...
## $ Age : int 67 18 18 71 36 31 23 37 30 23 ...
## $ Edu : int 6 3 3 1 6 4 2 2 6 2 ...
## $ Employment : int 2 6 7 5 5 3 5 1 3 5 ...
## $ CReligious : int 4 4 1 2 1 2 3 3 4 3 ...
## $ CPress : int 2 4 1 2 2 2 -1 4 3 2 ...
## $ CTelevision : int 3 4 3 2 2 2 3 4 3 2 ...
## $ CUnions : int 1 4 2 2 2 2 3 3 3 2 ...
## $ CCourts : int 2 4 1 2 1 2 3 3 4 1 ...
## $ CPParties : int 3 4 2 2 2 2 3 3 4 2 ...
## $ CParliament : int 2 4 1 2 2 2 3 3 4 2 ...
## $ CCivilService : int 2 4 1 2 2 2 3 3 3 1 ...
## $ CElections : int 2 4 1 2 2 2 2 2 2 3 ...
## $ CEnvOrg : int 1 4 1 2 2 2 2 2 -1 2 ...Show head of data
head(VC)## Country TPeople TFamily TNeighbourhood TKnow TMeet VFamily VFriends
## 39129 NLD 1 1 1 1 2 1 1
## 17644 TUN 2 3 4 2 4 1 2
## 78258 PHL 2 1 2 1 3 1 1
## 56142 SGP 2 1 2 2 3 1 2
## 31553 HKG 1 1 2 2 3 1 2
## 4791 VNM 2 1 2 2 2 1 2
## VLeisure VReligion HSatFin HMedicine EPrivate ECompetition EHardWork PIAB
## 39129 1 4 10 4 7 8 7 4
## 17644 1 2 10 4 3 1 1 4
## 78258 3 2 9 3 6 7 5 4
## 56142 2 2 10 4 6 5 6 2
## 31553 2 1 7 4 7 8 3 4
## 4791 2 2 10 4 1 1 5 2
## STOpportunity STFaith STImportant PNewspaper PMobile PEmail PSocial
## 39129 5 1 1 1 1 1 3
## 17644 8 8 1 5 5 5 1
## 78258 7 6 4 3 1 2 1
## 56142 10 6 6 2 1 2 1
## 31553 2 5 6 4 1 2 1
## 4791 10 4 2 2 1 5 1
## PDemImp PDemCurrent PSatisfied MF Age Edu Employment CReligious CPress
## 39129 10 7 6 2 67 6 2 4 2
## 17644 10 4 5 2 18 3 6 4 4
## 78258 7 7 8 2 18 3 7 1 1
## 56142 10 10 7 2 71 1 5 2 2
## 31553 8 8 8 2 36 6 5 1 2
## 4791 10 9 8 2 31 4 3 2 2
## CTelevision CUnions CCourts CPParties CParliament CCivilService
## 39129 3 1 2 3 2 2
## 17644 4 4 4 4 4 4
## 78258 3 2 1 2 1 1
## 56142 2 2 2 2 2 2
## 31553 2 2 1 2 2 2
## 4791 2 2 2 2 2 2
## CElections CEnvOrg
## 39129 2 1
## 17644 4 4
## 78258 1 1
## 56142 2 2
## 31553 2 2
## 4791 2 2Treat -ve numbers as NA
VC[VC == -1 | VC == -2 | VC == -3 | VC == -4 | VC == -5] <- NA
#View(VC)
any(VC < 0, na.rm = TRUE) ## [1] FALSEcolSums(is.na(VC)) ## Country TPeople TFamily TNeighbourhood TKnow
## 0 642 160 391 288
## TMeet VFamily VFriends VLeisure VReligion
## 669 77 160 269 459
## HSatFin HMedicine EPrivate ECompetition EHardWork
## 301 303 1741 809 701
## PIAB STOpportunity STFaith STImportant PNewspaper
## 2515 1432 1934 1776 472
## PMobile PEmail PSocial PDemImp PDemCurrent
## 497 1005 1888 926 1368
## PSatisfied MF Age Edu Employment
## 1806 42 269 520 622
## CReligious CPress CTelevision CUnions CCourts
## 1017 1117 739 3581 1769
## CPParties CParliament CCivilService CElections CEnvOrg
## 1650 1739 1666 1959 3257Show summary of data
summary(VC)## Country TPeople TFamily TNeighbourhood
## Length:50000 Min. :1.000 Min. :1.00 Min. :1.000
## Class :character 1st Qu.:2.000 1st Qu.:1.00 1st Qu.:2.000
## Mode :character Median :2.000 Median :1.00 Median :2.000
## Mean :1.757 Mean :1.27 Mean :2.182
## 3rd Qu.:2.000 3rd Qu.:1.00 3rd Qu.:3.000
## Max. :2.000 Max. :4.00 Max. :4.000
## NA's :642 NA's :160 NA's :391
## TKnow TMeet VFamily VFriends
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:1.000
## Median :2.000 Median :3.000 Median :1.000 Median :2.000
## Mean :2.066 Mean :3.012 Mean :1.114 Mean :1.712
## 3rd Qu.:2.000 3rd Qu.:4.000 3rd Qu.:1.000 3rd Qu.:2.000
## Max. :4.000 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :288 NA's :669 NA's :77 NA's :160
## VLeisure VReligion HSatFin HMedicine
## Min. :1.000 Min. :1.000 Min. : 1.000 Min. :1.000
## 1st Qu.:1.000 1st Qu.:1.000 1st Qu.: 5.000 1st Qu.:3.000
## Median :2.000 Median :2.000 Median : 6.000 Median :4.000
## Mean :1.785 Mean :1.984 Mean : 6.208 Mean :3.348
## 3rd Qu.:2.000 3rd Qu.:3.000 3rd Qu.: 8.000 3rd Qu.:4.000
## Max. :4.000 Max. :4.000 Max. :10.000 Max. :4.000
## NA's :269 NA's :459 NA's :301 NA's :303
## EPrivate ECompetition EHardWork PIAB
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. :1.000
## 1st Qu.: 4.000 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.:1.000
## Median : 5.000 Median : 4.000 Median : 4.000 Median :2.000
## Mean : 5.658 Mean : 4.069 Mean : 4.455 Mean :2.411
## 3rd Qu.: 8.000 3rd Qu.: 6.000 3rd Qu.: 7.000 3rd Qu.:3.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :4.000
## NA's :1741 NA's :809 NA's :701 NA's :2515
## STOpportunity STFaith STImportant PNewspaper
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. :1.000
## 1st Qu.: 6.000 1st Qu.: 3.000 1st Qu.: 2.000 1st Qu.:2.000
## Median : 8.000 Median : 5.000 Median : 5.000 Median :4.000
## Mean : 7.556 Mean : 5.531 Mean : 4.605 Mean :3.374
## 3rd Qu.:10.000 3rd Qu.: 8.000 3rd Qu.: 7.000 3rd Qu.:5.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :5.000
## NA's :1432 NA's :1934 NA's :1776 NA's :472
## PMobile PEmail PSocial PDemImp
## Min. :1.000 Min. :1.000 Min. :1.000 Min. : 1.000
## 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:1.000 1st Qu.: 7.000
## Median :1.000 Median :4.000 Median :2.000 Median : 9.000
## Mean :2.421 Mean :3.514 Mean :2.672 Mean : 8.367
## 3rd Qu.:5.000 3rd Qu.:5.000 3rd Qu.:5.000 3rd Qu.:10.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :10.000
## NA's :497 NA's :1005 NA's :1888 NA's :926
## PDemCurrent PSatisfied MF Age
## Min. : 1.000 Min. : 1.000 Min. :1.000 Min. : 16.0
## 1st Qu.: 5.000 1st Qu.: 3.000 1st Qu.:1.000 1st Qu.: 29.0
## Median : 6.000 Median : 5.000 Median :2.000 Median : 41.0
## Mean : 6.169 Mean : 5.342 Mean :1.526 Mean : 43.1
## 3rd Qu.: 8.000 3rd Qu.: 7.000 3rd Qu.:2.000 3rd Qu.: 55.0
## Max. :10.000 Max. :10.000 Max. :2.000 Max. :100.0
## NA's :1368 NA's :1806 NA's :42 NA's :269
## Edu Employment CReligious CPress
## Min. :0.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :2.000 Median :3.000
## Mean :3.547 Mean :3.129 Mean :2.192 Mean :2.704
## 3rd Qu.:5.000 3rd Qu.:5.000 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :8.000 Max. :8.000 Max. :4.000 Max. :4.000
## NA's :520 NA's :622 NA's :1017 NA's :1117
## CTelevision CUnions CCourts CPParties
## 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 :2.000 Median :3.000
## Mean :2.628 Mean :2.704 Mean :2.413 Mean :2.963
## 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:4.000
## Max. :4.000 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :739 NA's :3581 NA's :1769 NA's :1650
## CParliament CCivilService CElections CEnvOrg
## Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.00
## 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:2.000 1st Qu.:2.00
## Median :3.000 Median :3.00 Median :3.000 Median :2.00
## Mean :2.792 Mean :2.56 Mean :2.594 Mean :2.38
## 3rd Qu.:4.000 3rd Qu.:3.00 3rd Qu.:3.000 3rd Qu.:3.00
## Max. :4.000 Max. :4.00 Max. :4.000 Max. :4.00
## NA's :1739 NA's :1666 NA's :1959 NA's :3257Q1 Charts
trust_long <- VC %>%
select(TPeople, TFamily, TNeighbourhood, TKnow, TMeet) %>%
pivot_longer(cols = everything(), names_to = "Trust_Variable", values_to = "Response")
ggplot(trust_long, aes(x = factor(Response))) +
geom_bar(fill = "#66CCFF", color = "black") +
facet_wrap(~Trust_Variable, ncol = 3, scales = "free_y") +
xlab("Response") +
ylab("Number of Respondents") +
ggtitle("Distribution of Trust Variables") +
theme_minimal()
importance_long <- VC %>%
select(VFamily, VFriends, VLeisure, VReligion) %>%
pivot_longer(cols = everything(), names_to = "Value_Type", values_to = "Response")
ggplot(importance_long, aes(x = factor(Response))) +
geom_bar(fill = "#66CCFF", color = "black") +
facet_wrap(~Value_Type, ncol = 2) +
xlab("Importance Rating") +
ylab("Number of Respondents") +
ggtitle("Distribution of Importance in Life") +
theme_minimal() +
theme(panel.spacing.y = unit(2, "lines")) 
ggplot(VC, aes(x = HSatFin)) +
geom_histogram(binwidth = 1, fill = "#66CCFF", color = "black") +
xlab("Financial Satisfaction (1 = Not at all, 10 = Completely)") +
ylab("Number of Respondents") +
ggtitle("Distribution of Financial Satisfaction") +
theme_minimal()## Warning: Removed 301 rows containing non-finite outside the scale range
## (`stat_bin()`).
ggplot(VC, aes(x = factor(HMedicine))) +
geom_bar(fill = "#66CCFF", color = "black") +
xlab("Response (1 = Often, 4 = Never)") +
ylab("Number of Respondents") +
ggtitle("Access to Medicine in the Last 12 Months") +
theme_minimal()
econ_long <- VC %>%
select(EPrivate, ECompetition, EHardWork) %>%
pivot_longer(cols = everything(), names_to = "Variable", values_to = "Response")
ggplot(econ_long, aes(x = Response)) +
geom_histogram(binwidth = 1, fill = "#66CCFF", color = "black", boundary = 1, closed = "left") +
facet_wrap(~Variable, ncol = 1) +
scale_x_continuous(breaks = 1:10, limits = c(1, 10)) +
xlab("Response Scale (1 = Collectivist View, 10 = Individualist View)") +
ylab("Number of Respondents") +
ggtitle("Distribution of Economic Values") +
theme_minimal() +
theme(panel.spacing.y = unit(2, "lines"))## Warning: Removed 3251 rows containing non-finite outside the scale range
## (`stat_bin()`).
st_long <- VC %>%
select(STOpportunity, STFaith, STImportant) %>%
pivot_longer(cols = everything(), names_to = "Variable", values_to = "Response")
ggplot(st_long, aes(x = Response)) +
geom_histogram(binwidth = 1, fill = "#66CCFF", color = "black", boundary = 0.5, closed = "left") +
facet_wrap(~Variable, ncol = 1) +
scale_x_continuous(breaks = 1:10, limits = c(1, 10)) +
xlab("Rating (1 = Not at all, 10 = Completely)") +
ylab("Number of Respondents") +
ggtitle("Distribution of Democratic Values and Satisfaction") +
theme_minimal() +
theme(panel.spacing.y = unit(2, "lines"))## Warning: Removed 5142 rows containing non-finite outside the scale range
## (`stat_bin()`).## Warning: Removed 6 rows containing missing values or values outside the scale range
## (`geom_bar()`).
pol_long <- VC %>%
select(PDemImp, PDemCurrent, PSatisfied) %>%
pivot_longer(cols = everything(), names_to = "Variable", values_to = "Response")
ggplot(pol_long, aes(x = Response)) +
geom_histogram(binwidth = 1, fill = "#66CCFF", color = "black", boundary = 0.5, closed = "left") +
facet_wrap(~Variable, ncol = 1) +
scale_x_continuous(breaks = 1:10, limits = c(1, 10)) +
xlab("Rating (1 = Not at all, 10 = Completely)") +
ylab("Number of Respondents") +
ggtitle("Distribution of Democratic Values and Satisfaction") +
theme_minimal() +
theme(panel.spacing.y = unit(2, "lines"))## Warning: Removed 4100 rows containing non-finite outside the scale range (`stat_bin()`).
## Removed 6 rows containing missing values or values outside the scale range
## (`geom_bar()`).
confidence_data <- VC %>%
select(CReligious, CPress, CTelevision, CUnions, CCourts, CPParties, CParliament, CCivilService,
CElections, CEnvOrg) %>%
pivot_longer(cols = everything(), names_to = "Organisation", values_to = "Response") %>%
filter(!is.na(Response))
# Plot: Each facet is a separate organisation showing response distribution
ggplot(confidence_data, aes(x = factor(Response))) +
geom_bar(fill = "#66CCFF", color = "black") +
facet_wrap(~Organisation, ncol = 2) +
labs(title = "Confidence in Social Organisations",
x = "Response (1 = A great deal, 4 = None at all)",
y = "Number of Respondents") +
theme_minimal()
Q2
Separate into two datasets for focus country vs other countries
MalaysiaData <- VC %>% filter(Country == "MYS")
OtherCountriesData <- VC %>% filter(Country != "MYS")Combine both data into a single dataset
CombinedData <- bind_rows(MalaysiaData, OtherCountriesData)Show summary for Malaysia and Other Countries
summary(MalaysiaData)## Country TPeople TFamily TNeighbourhood
## Length:675 Min. :1.000 Min. :1.000 Min. :1.0
## Class :character 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:2.0
## Mode :character Median :2.000 Median :1.000 Median :2.0
## Mean :1.812 Mean :1.289 Mean :2.2
## 3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.:3.0
## Max. :2.000 Max. :3.000 Max. :4.0
##
## TKnow TMeet VFamily VFriends VLeisure
## Min. :1.000 Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:3.000 1st Qu.:1.00 1st Qu.:1.000 1st Qu.:1.000
## Median :2.000 Median :3.000 Median :1.00 Median :2.000 Median :2.000
## Mean :1.993 Mean :3.139 Mean :1.04 Mean :1.726 Mean :1.652
## 3rd Qu.:2.000 3rd Qu.:4.000 3rd Qu.:1.00 3rd Qu.:2.000 3rd Qu.:2.000
## Max. :4.000 Max. :4.000 Max. :4.00 Max. :4.000 Max. :4.000
##
## VReligion HSatFin HMedicine EPrivate
## Min. :1.000 Min. : 1.000 Min. :1.000 Min. : 1.000
## 1st Qu.:1.000 1st Qu.: 5.000 1st Qu.:3.000 1st Qu.: 4.000
## Median :1.000 Median : 6.000 Median :4.000 Median : 5.000
## Mean :1.401 Mean : 6.157 Mean :3.387 Mean : 5.348
## 3rd Qu.:2.000 3rd Qu.: 8.000 3rd Qu.:4.000 3rd Qu.: 7.000
## Max. :4.000 Max. :10.000 Max. :4.000 Max. :10.000
##
## ECompetition EHardWork PIAB STOpportunity
## Min. : 1.000 Min. : 1.000 Min. :1.000 Min. : 1.000
## 1st Qu.: 2.000 1st Qu.: 3.000 1st Qu.:1.000 1st Qu.: 6.000
## Median : 4.000 Median : 5.000 Median :2.000 Median : 8.000
## Mean : 4.089 Mean : 4.679 Mean :2.247 Mean : 7.477
## 3rd Qu.: 6.000 3rd Qu.: 7.000 3rd Qu.:3.000 3rd Qu.: 9.000
## Max. :10.000 Max. :10.000 Max. :4.000 Max. :10.000
##
## STFaith STImportant PNewspaper PMobile
## Min. : 1.000 Min. : 1.000 Min. :1.000 Min. :1.00
## 1st Qu.: 5.000 1st Qu.: 2.000 1st Qu.:1.000 1st Qu.:1.00
## Median : 6.000 Median : 4.000 Median :2.000 Median :1.00
## Mean : 6.194 Mean : 4.459 Mean :2.415 Mean :1.57
## 3rd Qu.: 8.000 3rd Qu.: 6.000 3rd Qu.:4.000 3rd Qu.:2.00
## Max. :10.000 Max. :10.000 Max. :5.000 Max. :5.00
##
## PEmail PSocial PDemImp PDemCurrent
## Min. :1.000 Min. :1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.:1.000 1st Qu.:1.000 1st Qu.: 7.000 1st Qu.: 4.000
## Median :2.000 Median :1.000 Median : 9.000 Median : 6.000
## Mean :2.535 Mean :1.684 Mean : 8.216 Mean : 5.956
## 3rd Qu.:4.000 3rd Qu.:2.000 3rd Qu.:10.000 3rd Qu.: 8.000
## Max. :5.000 Max. :5.000 Max. :10.000 Max. :10.000
##
## PSatisfied MF Age Edu
## Min. : 1.000 Min. :1.000 Min. :18.00 Min. :0.000
## 1st Qu.: 3.000 1st Qu.:1.000 1st Qu.:27.00 1st Qu.:2.000
## Median : 5.000 Median :1.000 Median :35.00 Median :2.000
## Mean : 5.179 Mean :1.483 Mean :38.55 Mean :3.366
## 3rd Qu.: 7.000 3rd Qu.:2.000 3rd Qu.:50.00 3rd Qu.:5.000
## Max. :10.000 Max. :2.000 Max. :79.00 Max. :8.000
##
## Employment CReligious CPress CTelevision
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:2.000
## Median :1.000 Median :2.000 Median :3.000 Median :3.000
## Mean :2.443 Mean :1.794 Mean :2.667 Mean :2.631
## 3rd Qu.:4.000 3rd Qu.:2.000 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :8.000 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :1 NA's :2 NA's :1
## CUnions CCourts CPParties CParliament CCivilService
## Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :2.000 Median :2.00 Median :3.000 Median :3.000 Median :2.000
## Mean :2.366 Mean :2.24 Mean :2.835 Mean :2.657 Mean :2.355
## 3rd Qu.:3.000 3rd Qu.:3.00 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :4.000 Max. :4.00 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :1 NA's :1 NA's :1 NA's :2 NA's :2
## CElections CEnvOrg
## Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :2.000
## Mean :2.654 Mean :2.076
## 3rd Qu.:3.000 3rd Qu.:2.000
## Max. :4.000 Max. :4.000
## NA's :1 NA's :2Show summary for Other Countries
summary(OtherCountriesData)## Country TPeople TFamily TNeighbourhood
## Length:49325 Min. :1.000 Min. :1.00 Min. :1.000
## Class :character 1st Qu.:2.000 1st Qu.:1.00 1st Qu.:2.000
## Mode :character Median :2.000 Median :1.00 Median :2.000
## Mean :1.756 Mean :1.27 Mean :2.182
## 3rd Qu.:2.000 3rd Qu.:1.00 3rd Qu.:3.000
## Max. :2.000 Max. :4.00 Max. :4.000
## NA's :642 NA's :160 NA's :391
## TKnow TMeet VFamily VFriends VLeisure
## Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:1.000
## Median :2.000 Median :3.00 Median :1.000 Median :2.000 Median :2.000
## Mean :2.067 Mean :3.01 Mean :1.115 Mean :1.712 Mean :1.787
## 3rd Qu.:2.000 3rd Qu.:4.00 3rd Qu.:1.000 3rd Qu.:2.000 3rd Qu.:2.000
## Max. :4.000 Max. :4.00 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :288 NA's :669 NA's :77 NA's :160 NA's :269
## VReligion HSatFin HMedicine EPrivate
## Min. :1.000 Min. : 1.000 Min. :1.000 Min. : 1.000
## 1st Qu.:1.000 1st Qu.: 5.000 1st Qu.:3.000 1st Qu.: 4.000
## Median :2.000 Median : 6.000 Median :4.000 Median : 5.000
## Mean :1.992 Mean : 6.208 Mean :3.347 Mean : 5.662
## 3rd Qu.:3.000 3rd Qu.: 8.000 3rd Qu.:4.000 3rd Qu.: 8.000
## Max. :4.000 Max. :10.000 Max. :4.000 Max. :10.000
## NA's :459 NA's :301 NA's :303 NA's :1741
## ECompetition EHardWork PIAB STOpportunity
## Min. : 1.000 Min. : 1.000 Min. :1.000 Min. : 1.000
## 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.:1.000 1st Qu.: 6.000
## Median : 4.000 Median : 4.000 Median :2.000 Median : 8.000
## Mean : 4.069 Mean : 4.452 Mean :2.413 Mean : 7.557
## 3rd Qu.: 6.000 3rd Qu.: 7.000 3rd Qu.:3.000 3rd Qu.:10.000
## Max. :10.000 Max. :10.000 Max. :4.000 Max. :10.000
## NA's :809 NA's :701 NA's :2515 NA's :1432
## STFaith STImportant PNewspaper PMobile
## Min. : 1.000 Min. : 1.000 Min. :1.000 Min. :1.000
## 1st Qu.: 3.000 1st Qu.: 2.000 1st Qu.:2.000 1st Qu.:1.000
## Median : 5.000 Median : 5.000 Median :4.000 Median :1.000
## Mean : 5.521 Mean : 4.607 Mean :3.387 Mean :2.433
## 3rd Qu.: 8.000 3rd Qu.: 7.000 3rd Qu.:5.000 3rd Qu.:5.000
## Max. :10.000 Max. :10.000 Max. :5.000 Max. :5.000
## NA's :1934 NA's :1776 NA's :472 NA's :497
## PEmail PSocial PDemImp PDemCurrent
## Min. :1.000 Min. :1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.:2.000 1st Qu.:1.000 1st Qu.: 7.000 1st Qu.: 5.000
## Median :4.000 Median :2.000 Median : 9.000 Median : 6.000
## Mean :3.528 Mean :2.686 Mean : 8.369 Mean : 6.172
## 3rd Qu.:5.000 3rd Qu.:5.000 3rd Qu.:10.000 3rd Qu.: 8.000
## Max. :5.000 Max. :5.000 Max. :10.000 Max. :10.000
## NA's :1005 NA's :1888 NA's :926 NA's :1368
## PSatisfied MF Age Edu
## Min. : 1.000 Min. :1.000 Min. : 16.00 Min. :0.00
## 1st Qu.: 3.000 1st Qu.:1.000 1st Qu.: 29.00 1st Qu.:2.00
## Median : 5.000 Median :2.000 Median : 41.00 Median :3.00
## Mean : 5.344 Mean :1.527 Mean : 43.16 Mean :3.55
## 3rd Qu.: 7.000 3rd Qu.:2.000 3rd Qu.: 55.00 3rd Qu.:6.00
## Max. :10.000 Max. :2.000 Max. :100.00 Max. :8.00
## NA's :1806 NA's :42 NA's :269 NA's :520
## Employment CReligious CPress CTelevision
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :2.000 Median :3.000 Median :3.000
## Mean :3.139 Mean :2.197 Mean :2.704 Mean :2.628
## 3rd Qu.:5.000 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :8.000 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :622 NA's :1016 NA's :1115 NA's :738
## CUnions CCourts CPParties CParliament
## 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 :2.000 Median :3.000 Median :3.000
## Mean :2.708 Mean :2.416 Mean :2.965 Mean :2.794
## 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :4.000 Max. :4.000 Max. :4.000 Max. :4.000
## NA's :3580 NA's :1768 NA's :1649 NA's :1737
## CCivilService CElections CEnvOrg
## Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :2.000
## Mean :2.563 Mean :2.593 Mean :2.385
## 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.:3.000
## Max. :4.000 Max. :4.000 Max. :4.000
## NA's :1664 NA's :1958 NA's :3255Add ‘Group’ Column
CombinedData <- CombinedData %>%
mutate(Group = ifelse(Country == "MYS", "Malaysia", "Others"))Graphs
trust_long <- CombinedData %>%
select(TPeople, TFamily, TNeighbourhood, TKnow, TMeet, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(trust_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Trustworthiness",
x = "Response",
y = "Frequency"
) +
scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
importance_long <- CombinedData %>%
select(VFriends, VLeisure, VReligion, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(importance_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Importance in Life",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
hw_long <- CombinedData %>%
select(HSatFin, HMedicine, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(hw_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Happiness and Wellbeing",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
e_long <- CombinedData %>%
select(EPrivate, ECompetition, EHardWork, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(e_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Economic Values",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
st_long <- CombinedData %>%
select(STOpportunity, STFaith, STImportant,Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(st_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Opinion on Science and Technology ",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
p1_long <- CombinedData %>%
select(PNewspaper, PMobile, PEmail, PSocial, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(p1_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Media Usage for Politic",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
p2_long <- CombinedData %>%
select( PDemImp, PDemCurrent, PSatisfied, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(p2_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Political Opinions",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
c_long <- CombinedData %>%
select( CReligious, CPress, CTelevision, CUnions, CCourts, CPParties, CParliament, CCivilService,
CElections, CEnvOrg, Group) %>%
pivot_longer(cols = -Group, names_to = "Variable", values_to = "Response") %>%
filter(!is.na(Response))
ggplot(c_long, aes(x = factor(Response), fill = Group)) +
geom_bar() +
facet_grid(Group ~ Variable, scales = "free_y") +
labs(
title = "Distribution of Confidence in Social Organisations",
x = "Response",
y = "Frequency"
) + scale_fill_manual(values = c("Malaysia" = "#FF6666", "Others" = "#66CCFF")) +
theme_minimal()
Hypothesis Testing
t.test(MalaysiaData$TKnow, OtherCountriesData$TKnow, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$TKnow and OtherCountriesData$TKnow
## t = -3.2307, df = 708.28, p-value = 0.000646
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.03643982
## sample estimates:
## mean of x mean of y
## 1.992593 2.066929t.test(MalaysiaData$VReligion, OtherCountriesData$VReligion,"less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$VReligion and OtherCountriesData$VReligion
## t = -21.416, df = 719.8, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.5446887
## sample estimates:
## mean of x mean of y
## 1.401481 1.991548t.test(MalaysiaData$VLeisure, MalaysiaData$VFriends,"less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$VLeisure and MalaysiaData$VFriends
## t = -2.2723, df = 1330.8, p-value = 0.01161
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.02041567
## sample estimates:
## mean of x mean of y
## 1.651852 1.725926t.test(OtherCountriesData$VFriends, OtherCountriesData$VLeisure,"less")##
## Welch Two Sample t-test
##
## data: OtherCountriesData$VFriends and OtherCountriesData$VLeisure
## t = -15.449, df = 97895, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.06764058
## sample estimates:
## mean of x mean of y
## 1.711522 1.787223t.test(MalaysiaData$HMedicine, OtherCountriesData$HMedicine,"greater")##
## Welch Two Sample t-test
##
## data: MalaysiaData$HMedicine and OtherCountriesData$HMedicine
## t = 1.2405, df = 698.5, p-value = 0.1076
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.01292976 Inf
## sample estimates:
## mean of x mean of y
## 3.386667 3.347211t.test(OtherCountriesData$HSatFin, MalaysiaData$HSatFin,"greater")##
## Welch Two Sample t-test
##
## data: OtherCountriesData$HSatFin and MalaysiaData$HSatFin
## t = 0.66318, df = 701.88, p-value = 0.2537
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.07627198 Inf
## sample estimates:
## mean of x mean of y
## 6.208449 6.157037t.test(MalaysiaData$EPrivate, OtherCountriesData$EPrivate,"less" )##
## Welch Two Sample t-test
##
## data: MalaysiaData$EPrivate and OtherCountriesData$EPrivate
## t = -3.4295, df = 701.98, p-value = 0.00032
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.1631174
## sample estimates:
## mean of x mean of y
## 5.348148 5.661987t.test(MalaysiaData$EHardWork, OtherCountriesData$EHardWork, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$EHardWork and OtherCountriesData$EHardWork
## t = 2.2875, df = 698.95, p-value = 0.9888
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.3900777
## sample estimates:
## mean of x mean of y
## 4.678519 4.451732t.test(MalaysiaData$ECompetition, OtherCountriesData$ECompetition, "greater")##
## Welch Two Sample t-test
##
## data: MalaysiaData$ECompetition and OtherCountriesData$ECompetition
## t = 0.22175, df = 699.82, p-value = 0.4123
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.1299001 Inf
## sample estimates:
## mean of x mean of y
## 4.088889 4.068678t.test(MalaysiaData$STOpportunity, OtherCountriesData$STOpportunity, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$STOpportunity and OtherCountriesData$STOpportunity
## t = -1.1959, df = 709.81, p-value = 0.1161
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.03031784
## sample estimates:
## mean of x mean of y
## 7.477037 7.557409t.test(MalaysiaData$STImportant, OtherCountriesData$STImportant, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$STImportant and OtherCountriesData$STImportant
## t = -1.518, df = 700.51, p-value = 0.06473
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.01257329
## sample estimates:
## mean of x mean of y
## 4.459259 4.607184t.test(MalaysiaData$STFaith, OtherCountriesData$STFaith, "greater")##
## Welch Two Sample t-test
##
## data: MalaysiaData$STFaith and OtherCountriesData$STFaith
## t = 8.0566, df = 710.94, p-value = 1.656e-15
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.5351212 Inf
## sample estimates:
## mean of x mean of y
## 6.194074 5.521449t.test(MalaysiaData$PNewspaper, OtherCountriesData$PNewspaper, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PNewspaper and OtherCountriesData$PNewspaper
## t = -17.855, df = 698.38, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.8828032
## sample estimates:
## mean of x mean of y
## 2.414815 3.387325t.test(MalaysiaData$PMobile, OtherCountriesData$PMobile, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PMobile and OtherCountriesData$PMobile
## t = -19.687, df = 718.77, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.7902458
## sample estimates:
## mean of x mean of y
## 1.570370 2.432764t.test(MalaysiaData$PEmail, OtherCountriesData$PEmail, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PEmail and OtherCountriesData$PEmail
## t = -16.232, df = 695.15, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.8921135
## sample estimates:
## mean of x mean of y
## 2.534815 3.527670t.test(MalaysiaData$PSocial, OtherCountriesData$PSocial, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PSocial and OtherCountriesData$PSocial
## t = -20.903, df = 715.6, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.9226826
## sample estimates:
## mean of x mean of y
## 1.684444 2.686047t.test(MalaysiaData$PDemImp, OtherCountriesData$PDemImp, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PDemImp and OtherCountriesData$PDemImp
## t = -2.069, df = 698, p-value = 0.01946
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.03111437
## sample estimates:
## mean of x mean of y
## 8.216296 8.368851t.test(MalaysiaData$PDemCurrent, OtherCountriesData$PDemCurrent, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PDemCurrent and OtherCountriesData$PDemCurrent
## t = -2.2401, df = 695.18, p-value = 0.0127
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.0573577
## sample estimates:
## mean of x mean of y
## 5.955556 6.172217t.test(MalaysiaData$PSatisfied, OtherCountriesData$PSatisfied, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$PSatisfied and OtherCountriesData$PSatisfied
## t = -1.6334, df = 695.3, p-value = 0.05142
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.001377133
## sample estimates:
## mean of x mean of y
## 5.179259 5.344052t.test(MalaysiaData$CReligious, OtherCountriesData$CReligious, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CReligious and OtherCountriesData$CReligious
## t = -14.694, df = 711.68, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.3581093
## sample estimates:
## mean of x mean of y
## 1.793769 2.197085t.test(MalaysiaData$CPress, OtherCountriesData$CPress, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CPress and OtherCountriesData$CPress
## t = -1.3631, df = 701.34, p-value = 0.08664
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.007768984
## sample estimates:
## mean of x mean of y
## 2.667162 2.704460t.test(MalaysiaData$CTelevision, OtherCountriesData$CTelevision, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CTelevision and OtherCountriesData$CTelevision
## t = 0.085813, df = 697.66, p-value = 0.5342
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf 0.05120508
## sample estimates:
## mean of x mean of y
## 2.630564 2.628028t.test(MalaysiaData$CUnions, OtherCountriesData$CUnions, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CUnions and OtherCountriesData$CUnions
## t = -13.473, df = 710.41, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.300194
## sample estimates:
## mean of x mean of y
## 2.366469 2.708471t.test(MalaysiaData$CCourts, OtherCountriesData$CCourts, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CCourts and OtherCountriesData$CCourts
## t = -5.8823, df = 702.02, p-value = 3.13e-09
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.1263172
## sample estimates:
## mean of x mean of y
## 2.240356 2.415796t.test(MalaysiaData$CPParties, OtherCountriesData$CPParties, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CPParties and OtherCountriesData$CPParties
## t = -4.3517, df = 699.4, p-value = 7.762e-06
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.08035167
## sample estimates:
## mean of x mean of y
## 2.835312 2.964594t.test(MalaysiaData$CParliament, OtherCountriesData$CParliament, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CParliament and OtherCountriesData$CParliament
## t = -4.3814, df = 698.71, p-value = 6.801e-06
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.08550639
## sample estimates:
## mean of x mean of y
## 2.656761 2.793772t.test(MalaysiaData$CCivilService, OtherCountriesData$CCivilService, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CCivilService and OtherCountriesData$CCivilService
## t = -7.3608, df = 700.79, p-value = 2.569e-13
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.1611138
## sample estimates:
## mean of x mean of y
## 2.355126 2.562682t.test(MalaysiaData$CElections, OtherCountriesData$CElections, "greater")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CElections and OtherCountriesData$CElections
## t = 1.8801, df = 698.28, p-value = 0.03026
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.007558222 Inf
## sample estimates:
## mean of x mean of y
## 2.654303 2.593324t.test(MalaysiaData$CEnvOrg, OtherCountriesData$CEnvOrg, "less")##
## Welch Two Sample t-test
##
## data: MalaysiaData$CEnvOrg and OtherCountriesData$CEnvOrg
## t = -11.988, df = 707.38, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
## -Inf -0.2666831
## sample estimates:
## mean of x mean of y
## 2.075780 2.384936Q2(b) Finding the best predictors for MALAYSIA
remove Group and Country columns
MalaysiaData$Country<- NULL
MalaysiaData$Group <- NULL
predictors <- names(MalaysiaData)[1:29]CReligious Regression Model
religious_fit <-lm(paste("CReligious ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(religious_fit)##
## Call:
## lm(formula = paste("CReligious ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.84757 -0.47371 0.00959 0.39773 1.86372
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.831869 0.339104 2.453 0.01443 *
## TPeople 0.044924 0.066224 0.678 0.49778
## TFamily 0.165844 0.057020 2.909 0.00376 **
## TNeighbourhood 0.146716 0.048634 3.017 0.00266 **
## TKnow 0.112644 0.046700 2.412 0.01614 *
## TMeet -0.053520 0.040880 -1.309 0.19094
## VFamily -0.095667 0.118709 -0.806 0.42060
## VFriends 0.039848 0.045199 0.882 0.37831
## VLeisure -0.006356 0.040041 -0.159 0.87393
## VReligion 0.305298 0.038381 7.954 8.11e-15 ***
## HSatFin -0.002863 0.013369 -0.214 0.83049
## HMedicine 0.032129 0.031548 1.018 0.30887
## EPrivate -0.028767 0.011143 -2.582 0.01005 *
## ECompetition -0.009855 0.012476 -0.790 0.42988
## EHardWork 0.022334 0.010601 2.107 0.03553 *
## PIAB -0.005779 0.025506 -0.227 0.82083
## STOpportunity -0.037552 0.015417 -2.436 0.01513 *
## STFaith -0.002095 0.011725 -0.179 0.85825
## STImportant -0.010899 0.010841 -1.005 0.31513
## PNewspaper 0.030630 0.018406 1.664 0.09657 .
## PMobile 0.024394 0.026384 0.925 0.35553
## PEmail -0.045189 0.018125 -2.493 0.01291 *
## PSocial -0.012469 0.024456 -0.510 0.61033
## PDemImp 0.006245 0.014378 0.434 0.66420
## PDemCurrent 0.008531 0.015519 0.550 0.58271
## PSatisfied -0.016111 0.015049 -1.071 0.28477
## MF 0.088179 0.050073 1.761 0.07871 .
## Age 0.003223 0.002017 1.598 0.11061
## Edu 0.003657 0.014969 0.244 0.80708
## Employment -0.003227 0.012628 -0.256 0.79839
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6115 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.2755, Adjusted R-squared: 0.2428
## F-statistic: 8.442 on 29 and 644 DF, p-value: < 2.2e-16CPress Regression Model
press_fit <-lm(paste("CPress ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(press_fit)##
## Call:
## lm(formula = paste("CPress ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.20475 -0.41530 0.04822 0.38929 1.98155
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5113657 0.3486950 7.202 1.66e-12 ***
## TPeople 0.0773325 0.0681901 1.134 0.257187
## TFamily -0.0014967 0.0586136 -0.026 0.979636
## TNeighbourhood 0.1182055 0.0499919 2.364 0.018351 *
## TKnow 0.0158757 0.0480303 0.331 0.741103
## TMeet 0.0525150 0.0420325 1.249 0.211977
## VFamily 0.0302391 0.1220230 0.248 0.804357
## VFriends 0.0311839 0.0464838 0.671 0.502554
## VLeisure 0.0858844 0.0411712 2.086 0.037369 *
## VReligion -0.0592176 0.0394676 -1.500 0.133998
## HSatFin -0.0120396 0.0137425 -0.876 0.381311
## HMedicine 0.0051642 0.0324288 0.159 0.873524
## EPrivate -0.0206135 0.0114539 -1.800 0.072377 .
## ECompetition -0.0155269 0.0128296 -1.210 0.226631
## EHardWork 0.0056361 0.0108972 0.517 0.605187
## PIAB -0.0513440 0.0262271 -1.958 0.050701 .
## STOpportunity 0.0103102 0.0158473 0.651 0.515540
## STFaith -0.0090734 0.0120546 -0.753 0.451913
## STImportant -0.0026860 0.0111711 -0.240 0.810066
## PNewspaper 0.0653459 0.0189245 3.453 0.000591 ***
## PMobile -0.0260262 0.0272197 -0.956 0.339354
## PEmail 0.0230649 0.0186337 1.238 0.216240
## PSocial -0.0102433 0.0251530 -0.407 0.683968
## PDemImp -0.0009136 0.0147842 -0.062 0.950743
## PDemCurrent -0.0131028 0.0159520 -0.821 0.411732
## PSatisfied -0.0789830 0.0154752 -5.104 4.39e-07 ***
## MF -0.0405846 0.0515042 -0.788 0.430995
## Age 0.0037938 0.0020746 1.829 0.067913 .
## Edu 0.0045820 0.0153872 0.298 0.765966
## Employment -0.0156706 0.0129834 -1.207 0.227888
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6285 on 643 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.2336, Adjusted R-squared: 0.199
## F-statistic: 6.758 on 29 and 643 DF, p-value: < 2.2e-16CTelevision Regression Model
tv_fit <-lm(paste("CTelevision ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(tv_fit)##
## Call:
## lm(formula = paste("CTelevision ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.17463 -0.42129 0.05246 0.43590 2.10916
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4549835 0.3794208 6.470 1.94e-10 ***
## TPeople 0.0638471 0.0740971 0.862 0.38919
## TFamily 0.0844186 0.0637990 1.323 0.18624
## TNeighbourhood 0.0889933 0.0544167 1.635 0.10245
## TKnow 0.0467594 0.0522520 0.895 0.37118
## TMeet 0.0818148 0.0457405 1.789 0.07414 .
## VFamily 0.0406716 0.1328229 0.306 0.75954
## VFriends 0.0350059 0.0505723 0.692 0.48906
## VLeisure 0.0717992 0.0448012 1.603 0.10951
## VReligion -0.0733203 0.0429439 -1.707 0.08824 .
## HSatFin -0.0242254 0.0149589 -1.619 0.10584
## HMedicine 0.0496394 0.0352989 1.406 0.16013
## EPrivate -0.0231641 0.0124679 -1.858 0.06364 .
## ECompetition -0.0208704 0.0139595 -1.495 0.13539
## EHardWork 0.0029452 0.0118619 0.248 0.80399
## PIAB -0.0331349 0.0285382 -1.161 0.24604
## STOpportunity -0.0038249 0.0172498 -0.222 0.82459
## STFaith 0.0044021 0.0131190 0.336 0.73732
## STImportant -0.0073010 0.0121300 -0.602 0.54746
## PNewspaper 0.0599172 0.0205943 2.909 0.00375 **
## PMobile -0.0333278 0.0295213 -1.129 0.25934
## PEmail 0.0021241 0.0202801 0.105 0.91661
## PSocial -0.0126438 0.0273634 -0.462 0.64419
## PDemImp -0.0038512 0.0160869 -0.239 0.81087
## PDemCurrent 0.0023979 0.0173643 0.138 0.89021
## PSatisfied -0.0894599 0.0168381 -5.313 1.49e-07 ***
## MF -0.0841934 0.0560259 -1.503 0.13339
## Age 0.0019397 0.0022571 0.859 0.39047
## Edu 0.0081554 0.0167483 0.487 0.62647
## Employment -0.0004848 0.0141288 -0.034 0.97264
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6842 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.2251, Adjusted R-squared: 0.1902
## F-statistic: 6.45 on 29 and 644 DF, p-value: < 2.2e-16CUnions Regression Model
unions_fit <-lm(paste("CUnions ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(unions_fit)##
## Call:
## lm(formula = paste("CUnions ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.69803 -0.38142 -0.05185 0.42261 1.95271
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.962174 0.324898 6.039 2.62e-09 ***
## TPeople -0.032196 0.063449 -0.507 0.61203
## TFamily 0.035216 0.054631 0.645 0.51941
## TNeighbourhood 0.132247 0.046597 2.838 0.00468 **
## TKnow 0.061483 0.044743 1.374 0.16988
## TMeet 0.068378 0.039168 1.746 0.08133 .
## VFamily 0.198849 0.113736 1.748 0.08088 .
## VFriends 0.057264 0.043305 1.322 0.18653
## VLeisure -0.054497 0.038363 -1.421 0.15593
## VReligion 0.019007 0.036773 0.517 0.60542
## HSatFin -0.014927 0.012809 -1.165 0.24433
## HMedicine 0.022133 0.030227 0.732 0.46430
## EPrivate -0.050609 0.010676 -4.740 2.63e-06 ***
## ECompetition 0.004307 0.011954 0.360 0.71873
## EHardWork 0.002247 0.010157 0.221 0.82502
## PIAB -0.033048 0.024437 -1.352 0.17674
## STOpportunity -0.005896 0.014771 -0.399 0.68991
## STFaith 0.005450 0.011234 0.485 0.62776
## STImportant 0.003884 0.010387 0.374 0.70861
## PNewspaper 0.047255 0.017635 2.680 0.00756 **
## PMobile -0.028632 0.025279 -1.133 0.25779
## PEmail -0.022293 0.017366 -1.284 0.19970
## PSocial 0.024589 0.023431 1.049 0.29439
## PDemImp -0.011765 0.013775 -0.854 0.39338
## PDemCurrent 0.006212 0.014869 0.418 0.67623
## PSatisfied -0.058762 0.014418 -4.075 5.17e-05 ***
## MF -0.050695 0.047975 -1.057 0.29105
## Age 0.005601 0.001933 2.898 0.00389 **
## Edu 0.009800 0.014342 0.683 0.49463
## Employment 0.004092 0.012099 0.338 0.73529
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5859 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.223, Adjusted R-squared: 0.188
## F-statistic: 6.374 on 29 and 644 DF, p-value: < 2.2e-16CCourts Regression Model
courts_fit <-lm(paste("CCourts ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(courts_fit)##
## Call:
## lm(formula = paste("CCourts ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.91448 -0.41149 -0.01823 0.40831 2.14388
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.097440 0.368601 5.690 1.93e-08 ***
## TPeople 0.038188 0.071984 0.531 0.595944
## TFamily 0.110649 0.061980 1.785 0.074691 .
## TNeighbourhood 0.119815 0.052865 2.266 0.023755 *
## TKnow -0.008814 0.050762 -0.174 0.862210
## TMeet 0.046552 0.044436 1.048 0.295207
## VFamily 0.087456 0.129035 0.678 0.498163
## VFriends 0.034297 0.049130 0.698 0.485383
## VLeisure -0.019010 0.043524 -0.437 0.662429
## VReligion 0.084604 0.041719 2.028 0.042977 *
## HSatFin -0.001990 0.014532 -0.137 0.891140
## HMedicine -0.045513 0.034292 -1.327 0.184910
## EPrivate -0.027752 0.012112 -2.291 0.022273 *
## ECompetition -0.002480 0.013561 -0.183 0.854982
## EHardWork -0.005767 0.011524 -0.500 0.616927
## PIAB -0.074923 0.027724 -2.702 0.007065 **
## STOpportunity 0.007374 0.016758 0.440 0.660044
## STFaith 0.005924 0.012745 0.465 0.642228
## STImportant 0.036502 0.011784 3.098 0.002036 **
## PNewspaper 0.043813 0.020007 2.190 0.028893 *
## PMobile -0.028157 0.028679 -0.982 0.326582
## PEmail -0.014407 0.019702 -0.731 0.464890
## PSocial 0.039070 0.026583 1.470 0.142126
## PDemImp -0.001584 0.015628 -0.101 0.919283
## PDemCurrent -0.032207 0.016869 -1.909 0.056675 .
## PSatisfied -0.072538 0.016358 -4.434 1.09e-05 ***
## MF -0.115110 0.054428 -2.115 0.034822 *
## Age 0.007598 0.002193 3.465 0.000566 ***
## Edu -0.003847 0.016271 -0.236 0.813175
## Employment -0.021353 0.013726 -1.556 0.120286
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6647 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.2798, Adjusted R-squared: 0.2474
## F-statistic: 8.629 on 29 and 644 DF, p-value: < 2.2e-16CPParties Regression Model
pparties_fit <-lm(paste("CPParties ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(pparties_fit)##
## Call:
## lm(formula = paste("CPParties ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.49944 -0.45367 0.02017 0.40673 2.20180
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.7685707 0.3693735 7.495 2.20e-13 ***
## TPeople 0.0050290 0.0721349 0.070 0.94444
## TFamily 0.1242695 0.0621096 2.001 0.04583 *
## TNeighbourhood 0.0892726 0.0529757 1.685 0.09244 .
## TKnow 0.0269689 0.0508683 0.530 0.59618
## TMeet 0.1211178 0.0445293 2.720 0.00671 **
## VFamily -0.3755175 0.1293057 -2.904 0.00381 **
## VFriends 0.0546851 0.0492331 1.111 0.26710
## VLeisure 0.1010592 0.0436148 2.317 0.02081 *
## VReligion 0.0534902 0.0418067 1.279 0.20119
## HSatFin -0.0246700 0.0145628 -1.694 0.09074 .
## HMedicine -0.0267239 0.0343642 -0.778 0.43705
## EPrivate -0.0231530 0.0121377 -1.908 0.05690 .
## ECompetition -0.0195661 0.0135899 -1.440 0.15042
## EHardWork -0.0080502 0.0115478 -0.697 0.48598
## PIAB -0.0358835 0.0277825 -1.292 0.19696
## STOpportunity 0.0336396 0.0167930 2.003 0.04558 *
## STFaith 0.0037755 0.0127716 0.296 0.76762
## STImportant 0.0105486 0.0118088 0.893 0.37204
## PNewspaper 0.0799062 0.0200490 3.986 7.50e-05 ***
## PMobile -0.0611096 0.0287395 -2.126 0.03386 *
## PEmail -0.0205007 0.0197430 -1.038 0.29948
## PSocial 0.0008734 0.0266388 0.033 0.97386
## PDemImp -0.0182233 0.0156609 -1.164 0.24501
## PDemCurrent -0.0082236 0.0169045 -0.486 0.62680
## PSatisfied -0.0843937 0.0163922 -5.148 3.49e-07 ***
## MF 0.0065304 0.0545423 0.120 0.90473
## Age 0.0037714 0.0021974 1.716 0.08659 .
## Edu 0.0032411 0.0163048 0.199 0.84250
## Employment -0.0050819 0.0137547 -0.369 0.71190
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6661 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.2725, Adjusted R-squared: 0.2398
## F-statistic: 8.319 on 29 and 644 DF, p-value: < 2.2e-16CParliament Regression Model
parliament_fit <-lm(paste("CParliament ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(parliament_fit)##
## Call:
## lm(formula = paste("CParliament ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.27151 -0.46743 -0.00139 0.43898 2.07331
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.9614505 0.3755208 5.223 2.38e-07 ***
## TPeople 0.0736642 0.0734763 1.003 0.31645
## TFamily 0.0471001 0.0631304 0.746 0.45589
## TNeighbourhood 0.1419993 0.0539156 2.634 0.00865 **
## TKnow 0.0617029 0.0517310 1.193 0.23340
## TMeet 0.0815982 0.0452868 1.802 0.07204 .
## VFamily 0.1198413 0.1314430 0.912 0.36225
## VFriends 0.0813080 0.0500671 1.624 0.10487
## VLeisure 0.0940626 0.0443530 2.121 0.03432 *
## VReligion -0.0198660 0.0425030 -0.467 0.64037
## HSatFin -0.0310949 0.0148044 -2.100 0.03608 *
## HMedicine -0.0082341 0.0349372 -0.236 0.81375
## EPrivate -0.0242420 0.0123440 -1.964 0.04998 *
## ECompetition 0.0008545 0.0138251 0.062 0.95074
## EHardWork -0.0057952 0.0117403 -0.494 0.62174
## PIAB -0.0641828 0.0282429 -2.273 0.02338 *
## STOpportunity 0.0464865 0.0170759 2.722 0.00666 **
## STFaith -0.0112668 0.0129821 -0.868 0.38579
## STImportant 0.0257292 0.0120198 2.141 0.03268 *
## PNewspaper 0.0962606 0.0203851 4.722 2.87e-06 ***
## PMobile -0.0739562 0.0292248 -2.531 0.01162 *
## PEmail 0.0086139 0.0200679 0.429 0.66789
## PSocial 0.0195411 0.0270921 0.721 0.47100
## PDemImp -0.0303471 0.0159187 -1.906 0.05705 .
## PDemCurrent -0.0132684 0.0171824 -0.772 0.44027
## PSatisfied -0.1037145 0.0166621 -6.225 8.71e-10 ***
## MF -0.0437682 0.0554872 -0.789 0.43052
## Age 0.0060115 0.0022366 2.688 0.00738 **
## Edu 0.0213352 0.0165755 1.287 0.19851
## Employment -0.0014379 0.0140258 -0.103 0.91838
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.677 on 643 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.3205, Adjusted R-squared: 0.2899
## F-statistic: 10.46 on 29 and 643 DF, p-value: < 2.2e-16CCivilService Regression Model
civilService_fit <-lm(paste("CCivilService ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(civilService_fit)##
## Call:
## lm(formula = paste("CCivilService ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.92472 -0.41276 -0.01511 0.41946 2.16233
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.760126 0.338538 5.199 2.69e-07 ***
## TPeople 0.049450 0.066240 0.747 0.45562
## TFamily 0.007559 0.056913 0.133 0.89438
## TNeighbourhood 0.133846 0.048606 2.754 0.00606 **
## TKnow 0.078264 0.046636 1.678 0.09380 .
## TMeet 0.054172 0.040827 1.327 0.18502
## VFamily 0.085243 0.118498 0.719 0.47218
## VFriends -0.002189 0.045136 -0.048 0.96133
## VLeisure 0.050749 0.039985 1.269 0.20483
## VReligion 0.093911 0.038317 2.451 0.01452 *
## HSatFin -0.011527 0.013346 -0.864 0.38807
## HMedicine -0.012175 0.031496 -0.387 0.69922
## EPrivate -0.050061 0.011128 -4.499 8.12e-06 ***
## ECompetition 0.004043 0.012464 0.324 0.74575
## EHardWork 0.007423 0.010584 0.701 0.48335
## PIAB -0.008320 0.025461 -0.327 0.74396
## STOpportunity 0.001812 0.015394 0.118 0.90631
## STFaith -0.002818 0.011704 -0.241 0.80978
## STImportant 0.029202 0.010836 2.695 0.00722 **
## PNewspaper 0.039726 0.018378 2.162 0.03101 *
## PMobile -0.053341 0.026347 -2.025 0.04332 *
## PEmail -0.009670 0.018092 -0.534 0.59318
## PSocial 0.056244 0.024424 2.303 0.02161 *
## PDemImp 0.001886 0.014351 0.131 0.89549
## PDemCurrent -0.032658 0.015490 -2.108 0.03539 *
## PSatisfied -0.072825 0.015021 -4.848 1.56e-06 ***
## MF 0.026377 0.050023 0.527 0.59817
## Age 0.004514 0.002016 2.239 0.02551 *
## Edu 0.019639 0.014943 1.314 0.18924
## Employment -0.004138 0.012645 -0.327 0.74357
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6103 on 643 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.3198, Adjusted R-squared: 0.2892
## F-statistic: 10.43 on 29 and 643 DF, p-value: < 2.2e-16CElections Regression Model
elections_fit <-lm(paste("CElections ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(elections_fit)##
## Call:
## lm(formula = paste("CElections ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.32021 -0.45047 0.01843 0.44908 2.04721
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.607318 0.390625 6.675 5.35e-11 ***
## TPeople -0.031518 0.076285 -0.413 0.67963
## TFamily 0.025295 0.065683 0.385 0.70028
## TNeighbourhood 0.041372 0.056024 0.738 0.46050
## TKnow 0.045190 0.053795 0.840 0.40119
## TMeet 0.145437 0.047091 3.088 0.00210 **
## VFamily -0.211551 0.136745 -1.547 0.12234
## VFriends -0.001922 0.052066 -0.037 0.97057
## VLeisure 0.039531 0.046124 0.857 0.39173
## VReligion 0.114499 0.044212 2.590 0.00982 **
## HSatFin -0.025282 0.015401 -1.642 0.10116
## HMedicine 0.008783 0.036341 0.242 0.80909
## EPrivate -0.021529 0.012836 -1.677 0.09398 .
## ECompetition -0.003139 0.014372 -0.218 0.82719
## EHardWork -0.003868 0.012212 -0.317 0.75156
## PIAB -0.078768 0.029381 -2.681 0.00753 **
## STOpportunity 0.023687 0.017759 1.334 0.18275
## STFaith 0.027909 0.013506 2.066 0.03919 *
## STImportant 0.008692 0.012488 0.696 0.48666
## PNewspaper 0.053467 0.021202 2.522 0.01192 *
## PMobile -0.051030 0.030393 -1.679 0.09364 .
## PEmail 0.038076 0.020879 1.824 0.06867 .
## PSocial -0.000962 0.028171 -0.034 0.97277
## PDemImp -0.024536 0.016562 -1.481 0.13897
## PDemCurrent -0.030937 0.017877 -1.731 0.08402 .
## PSatisfied -0.112008 0.017335 -6.461 2.05e-10 ***
## MF 0.003437 0.057680 0.060 0.95250
## Age 0.004820 0.002324 2.074 0.03845 *
## Edu 0.038872 0.017243 2.254 0.02451 *
## Employment -0.003195 0.014546 -0.220 0.82619
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7044 on 644 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.3179, Adjusted R-squared: 0.2872
## F-statistic: 10.35 on 29 and 644 DF, p-value: < 2.2e-16CEnvOrg Regression Model
envOrg_fit <-lm(paste("CEnvOrg ~", paste(predictors, collapse = " + ")), data = MalaysiaData)
summary(envOrg_fit)##
## Call:
## lm(formula = paste("CEnvOrg ~", paste(predictors, collapse = " + ")),
## data = MalaysiaData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.66566 -0.32269 -0.04139 0.34109 2.07727
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.365984 0.331492 4.121 4.27e-05 ***
## TPeople 0.084878 0.064717 1.312 0.190151
## TFamily 0.059408 0.055867 1.063 0.288013
## TNeighbourhood 0.122552 0.047650 2.572 0.010337 *
## TKnow 0.018990 0.045694 0.416 0.677845
## TMeet 0.011756 0.039959 0.294 0.768703
## VFamily 0.301206 0.116153 2.593 0.009726 **
## VFriends 0.088966 0.044304 2.008 0.045051 *
## VLeisure 0.056206 0.039248 1.432 0.152610
## VReligion 0.041347 0.037522 1.102 0.270896
## HSatFin -0.005520 0.013065 -0.423 0.672772
## HMedicine 0.042734 0.030830 1.386 0.166194
## EPrivate -0.042245 0.010958 -3.855 0.000127 ***
## ECompetition 0.004173 0.012220 0.341 0.732846
## EHardWork 0.005809 0.010367 0.560 0.575422
## PIAB -0.038453 0.024926 -1.543 0.123397
## STOpportunity -0.018621 0.015114 -1.232 0.218387
## STFaith 0.003381 0.011468 0.295 0.768230
## STImportant 0.024992 0.010595 2.359 0.018635 *
## PNewspaper 0.025014 0.018039 1.387 0.166026
## PMobile -0.053250 0.025936 -2.053 0.040461 *
## PEmail 0.005943 0.017712 0.336 0.737334
## PSocial 0.038486 0.024141 1.594 0.111386
## PDemImp -0.033050 0.014093 -2.345 0.019320 *
## PDemCurrent -0.026035 0.015168 -1.716 0.086558 .
## PSatisfied -0.020288 0.014710 -1.379 0.168303
## MF -0.035830 0.049008 -0.731 0.464981
## Age 0.005134 0.001972 2.604 0.009433 **
## Edu 0.015872 0.014629 1.085 0.278332
## Employment -0.016833 0.012344 -1.364 0.173151
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5975 on 643 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.2168, Adjusted R-squared: 0.1815
## F-statistic: 6.138 on 29 and 643 DF, p-value: < 2.2e-16Q2(c) Finding the best predictors for OTHER COUNTRIES
CReligious Regression Model
religious_fit1 <-lm(paste("CReligious ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(religious_fit1)##
## Call:
## lm(formula = paste("CReligious ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.71911 -0.62611 -0.08408 0.51104 2.92032
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.583e-01 5.006e-02 17.146 < 2e-16 ***
## TPeople 3.055e-02 1.095e-02 2.791 0.00526 **
## TFamily 1.255e-01 8.180e-03 15.338 < 2e-16 ***
## TNeighbourhood 1.046e-01 6.459e-03 16.202 < 2e-16 ***
## TKnow 2.523e-04 6.419e-03 0.039 0.96865
## TMeet 3.031e-02 6.093e-03 4.974 6.59e-07 ***
## VFamily 3.992e-02 1.228e-02 3.251 0.00115 **
## VFriends -7.604e-04 6.226e-03 -0.122 0.90279
## VLeisure -6.806e-02 5.624e-03 -12.102 < 2e-16 ***
## VReligion 4.632e-01 4.264e-03 108.634 < 2e-16 ***
## HSatFin -1.424e-02 1.876e-03 -7.591 3.24e-14 ***
## HMedicine 3.662e-02 4.858e-03 7.537 4.90e-14 ***
## EPrivate -2.577e-03 1.529e-03 -1.686 0.09185 .
## ECompetition -1.205e-05 1.651e-03 -0.007 0.99418
## EHardWork 1.273e-02 1.522e-03 8.359 < 2e-16 ***
## PIAB -7.680e-03 3.929e-03 -1.955 0.05062 .
## STOpportunity -8.090e-03 1.887e-03 -4.288 1.81e-05 ***
## STFaith -1.562e-03 1.493e-03 -1.046 0.29551
## STImportant -6.334e-03 1.508e-03 -4.200 2.68e-05 ***
## PNewspaper 1.979e-02 2.854e-03 6.932 4.23e-12 ***
## PMobile 9.622e-03 3.097e-03 3.107 0.00189 **
## PEmail -7.345e-03 3.155e-03 -2.328 0.01989 *
## PSocial -3.375e-02 3.136e-03 -10.762 < 2e-16 ***
## PDemImp 6.847e-03 2.096e-03 3.267 0.00109 **
## PDemCurrent -1.467e-02 2.089e-03 -7.022 2.22e-12 ***
## PSatisfied -2.011e-02 1.994e-03 -10.087 < 2e-16 ***
## MF -2.745e-02 8.603e-03 -3.191 0.00142 **
## Age 3.362e-03 2.936e-04 11.452 < 2e-16 ***
## Edu 2.337e-02 2.358e-03 9.910 < 2e-16 ***
## Employment -4.663e-03 2.121e-03 -2.199 0.02789 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8166 on 37663 degrees of freedom
## (11632 observations deleted due to missingness)
## Multiple R-squared: 0.3272, Adjusted R-squared: 0.3266
## F-statistic: 631.5 on 29 and 37663 DF, p-value: < 2.2e-16CPress Regression Model
press_fit1 <-lm(paste("CPress ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(press_fit1)##
## Call:
## lm(formula = paste("CPress ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.52120 -0.57174 0.05916 0.54732 2.24470
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.9091704 0.0501795 38.047 < 2e-16 ***
## TPeople 0.1003115 0.0109518 9.159 < 2e-16 ***
## TFamily 0.0579296 0.0082026 7.062 1.67e-12 ***
## TNeighbourhood 0.1220080 0.0064704 18.856 < 2e-16 ***
## TKnow 0.0251641 0.0064396 3.908 9.33e-05 ***
## TMeet 0.0817680 0.0061124 13.377 < 2e-16 ***
## VFamily 0.0030697 0.0122629 0.250 0.802340
## VFriends 0.0104522 0.0062433 1.674 0.094114 .
## VLeisure -0.0251203 0.0056401 -4.454 8.46e-06 ***
## VReligion 0.0415268 0.0042513 9.768 < 2e-16 ***
## HSatFin -0.0017157 0.0018816 -0.912 0.361861
## HMedicine 0.0096338 0.0048686 1.979 0.047848 *
## EPrivate -0.0038450 0.0015336 -2.507 0.012177 *
## ECompetition -0.0059695 0.0016560 -3.605 0.000313 ***
## EHardWork 0.0049086 0.0015257 3.217 0.001296 **
## PIAB -0.0173750 0.0039338 -4.417 1.00e-05 ***
## STOpportunity -0.0150298 0.0018900 -7.952 1.88e-15 ***
## STFaith 0.0063083 0.0014963 4.216 2.50e-05 ***
## STImportant 0.0017947 0.0015114 1.188 0.235036
## PNewspaper 0.0579735 0.0028530 20.320 < 2e-16 ***
## PMobile 0.0213940 0.0031014 6.898 5.35e-12 ***
## PEmail -0.0041654 0.0031538 -1.321 0.186584
## PSocial -0.0210196 0.0031370 -6.701 2.11e-11 ***
## PDemImp 0.0077374 0.0020996 3.685 0.000229 ***
## PDemCurrent -0.0228283 0.0020946 -10.898 < 2e-16 ***
## PSatisfied -0.0503727 0.0019982 -25.209 < 2e-16 ***
## MF 0.0169808 0.0086136 1.971 0.048686 *
## Age 0.0015929 0.0002943 5.413 6.23e-08 ***
## Edu 0.0285736 0.0023621 12.097 < 2e-16 ***
## Employment -0.0065466 0.0021236 -3.083 0.002052 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8177 on 37666 degrees of freedom
## (11629 observations deleted due to missingness)
## Multiple R-squared: 0.1239, Adjusted R-squared: 0.1232
## F-statistic: 183.6 on 29 and 37666 DF, p-value: < 2.2e-16CCTelevision Regression Model
tv_fit1 <-lm(paste("CTelevision ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(tv_fit1)##
## Call:
## lm(formula = paste("CTelevision ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.69178 -0.55195 0.04084 0.54491 2.28116
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.0113050 0.0497427 40.434 < 2e-16 ***
## TPeople 0.0489470 0.0108698 4.503 6.72e-06 ***
## TFamily 0.0764083 0.0081367 9.391 < 2e-16 ***
## TNeighbourhood 0.1229000 0.0064129 19.165 < 2e-16 ***
## TKnow 0.0298230 0.0063771 4.677 2.93e-06 ***
## TMeet 0.0649741 0.0060596 10.723 < 2e-16 ***
## VFamily 0.0206484 0.0121786 1.695 0.089994 .
## VFriends -0.0037921 0.0061883 -0.613 0.540026
## VLeisure -0.0242735 0.0055870 -4.345 1.40e-05 ***
## VReligion 0.0548746 0.0042214 12.999 < 2e-16 ***
## HSatFin 0.0002839 0.0018660 0.152 0.879068
## HMedicine 0.0107026 0.0048266 2.217 0.026600 *
## EPrivate -0.0057524 0.0015201 -3.784 0.000154 ***
## ECompetition -0.0033084 0.0016416 -2.015 0.043869 *
## EHardWork 0.0095399 0.0015129 6.306 2.90e-10 ***
## PIAB -0.0113266 0.0039034 -2.902 0.003713 **
## STOpportunity -0.0174042 0.0018742 -9.286 < 2e-16 ***
## STFaith 0.0044723 0.0014842 3.013 0.002586 **
## STImportant -0.0013409 0.0014988 -0.895 0.370983
## PNewspaper 0.0404341 0.0028337 14.269 < 2e-16 ***
## PMobile 0.0244197 0.0030754 7.940 2.07e-15 ***
## PEmail -0.0190288 0.0031339 -6.072 1.28e-09 ***
## PSocial -0.0168399 0.0031136 -5.408 6.39e-08 ***
## PDemImp 0.0160958 0.0020812 7.734 1.07e-14 ***
## PDemCurrent -0.0256792 0.0020762 -12.368 < 2e-16 ***
## PSatisfied -0.0539080 0.0019804 -27.221 < 2e-16 ***
## MF -0.0339314 0.0085460 -3.970 7.19e-05 ***
## Age 0.0015468 0.0002918 5.301 1.16e-07 ***
## Edu 0.0390766 0.0023429 16.679 < 2e-16 ***
## Employment -0.0074566 0.0021073 -3.539 0.000403 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8133 on 37857 degrees of freedom
## (11438 observations deleted due to missingness)
## Multiple R-squared: 0.1275, Adjusted R-squared: 0.1269
## F-statistic: 190.8 on 29 and 37857 DF, p-value: < 2.2e-16CUnions Regression Model
unions_fit1 <-lm(paste("CUnions ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(unions_fit1)##
## Call:
## lm(formula = paste("CUnions ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.73303 -0.58858 0.06318 0.55349 2.39630
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.8303954 0.0517112 35.397 < 2e-16 ***
## TPeople 0.0805995 0.0112958 7.135 9.83e-13 ***
## TFamily 0.0536544 0.0083956 6.391 1.67e-10 ***
## TNeighbourhood 0.1150891 0.0066787 17.232 < 2e-16 ***
## TKnow 0.0638419 0.0066366 9.620 < 2e-16 ***
## TMeet 0.1052323 0.0063149 16.664 < 2e-16 ***
## VFamily 0.0160011 0.0125990 1.270 0.204082
## VFriends 0.0271758 0.0064470 4.215 2.50e-05 ***
## VLeisure -0.0309708 0.0058322 -5.310 1.10e-07 ***
## VReligion 0.0233110 0.0043950 5.304 1.14e-07 ***
## HSatFin -0.0008336 0.0019418 -0.429 0.667715
## HMedicine -0.0002425 0.0050224 -0.048 0.961490
## EPrivate -0.0118732 0.0015854 -7.489 7.10e-14 ***
## ECompetition -0.0057822 0.0017114 -3.379 0.000729 ***
## EHardWork 0.0074787 0.0015788 4.737 2.18e-06 ***
## PIAB -0.0015799 0.0040670 -0.388 0.697673
## STOpportunity -0.0154456 0.0019484 -7.927 2.30e-15 ***
## STFaith 0.0119306 0.0015463 7.716 1.23e-14 ***
## STImportant 0.0079120 0.0015656 5.054 4.35e-07 ***
## PNewspaper 0.0276107 0.0029455 9.374 < 2e-16 ***
## PMobile 0.0264199 0.0032103 8.230 < 2e-16 ***
## PEmail -0.0147523 0.0032520 -4.536 5.74e-06 ***
## PSocial -0.0068863 0.0032457 -2.122 0.033872 *
## PDemImp 0.0004242 0.0021649 0.196 0.844669
## PDemCurrent -0.0196348 0.0021556 -9.109 < 2e-16 ***
## PSatisfied -0.0430130 0.0020562 -20.919 < 2e-16 ***
## MF -0.0244913 0.0088869 -2.756 0.005856 **
## Age 0.0032592 0.0003048 10.692 < 2e-16 ***
## Edu 0.0290188 0.0024367 11.909 < 2e-16 ***
## Employment 0.0049510 0.0021924 2.258 0.023938 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8292 on 36318 degrees of freedom
## (12977 observations deleted due to missingness)
## Multiple R-squared: 0.1164, Adjusted R-squared: 0.1157
## F-statistic: 164.9 on 29 and 36318 DF, p-value: < 2.2e-16CCourts Regression Model
courts_fit1 <-lm(paste("CCourts ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(courts_fit1)##
## Call:
## lm(formula = paste("CCourts ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7712 -0.5773 -0.0483 0.6045 2.7906
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.7582225 0.0524567 33.518 < 2e-16 ***
## TPeople 0.1306002 0.0114452 11.411 < 2e-16 ***
## TFamily 0.1029577 0.0085681 12.016 < 2e-16 ***
## TNeighbourhood 0.1189688 0.0067644 17.587 < 2e-16 ***
## TKnow 0.0859663 0.0067231 12.787 < 2e-16 ***
## TMeet 0.0399095 0.0063848 6.251 4.13e-10 ***
## VFamily 0.0358750 0.0128445 2.793 0.005224 **
## VFriends 0.0426352 0.0065282 6.531 6.62e-11 ***
## VLeisure -0.0451438 0.0058876 -7.668 1.79e-14 ***
## VReligion 0.0292720 0.0044504 6.577 4.85e-11 ***
## HSatFin -0.0078607 0.0019661 -3.998 6.40e-05 ***
## HMedicine -0.0299411 0.0050857 -5.887 3.96e-09 ***
## EPrivate -0.0003851 0.0016027 -0.240 0.810114
## ECompetition 0.0047792 0.0017305 2.762 0.005753 **
## EHardWork 0.0085654 0.0015955 5.368 7.99e-08 ***
## PIAB 0.0074118 0.0041139 1.802 0.071610 .
## STOpportunity -0.0118556 0.0019749 -6.003 1.95e-09 ***
## STFaith 0.0216174 0.0015633 13.828 < 2e-16 ***
## STImportant 0.0103402 0.0015805 6.542 6.13e-11 ***
## PNewspaper 0.0078457 0.0029862 2.627 0.008609 **
## PMobile 0.0152345 0.0032428 4.698 2.64e-06 ***
## PEmail 0.0045003 0.0032992 1.364 0.172557
## PSocial -0.0103212 0.0032813 -3.145 0.001659 **
## PDemImp 0.0062224 0.0021944 2.836 0.004576 **
## PDemCurrent -0.0393886 0.0021874 -18.007 < 2e-16 ***
## PSatisfied -0.0615576 0.0020873 -29.491 < 2e-16 ***
## MF -0.0308125 0.0090037 -3.422 0.000622 ***
## Age 0.0014461 0.0003079 4.697 2.65e-06 ***
## Edu 0.0249583 0.0024681 10.112 < 2e-16 ***
## Employment -0.0014405 0.0022201 -0.649 0.516450
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8543 on 37627 degrees of freedom
## (11668 observations deleted due to missingness)
## Multiple R-squared: 0.1653, Adjusted R-squared: 0.1647
## F-statistic: 257 on 29 and 37627 DF, p-value: < 2.2e-16CPParties Regression Model
pparties_fit1 <-lm(paste("CPParties ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(pparties_fit1)##
## Call:
## lm(formula = paste("CPParties ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0593 -0.5426 0.0812 0.5667 2.2098
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5479291 0.0495333 51.439 < 2e-16 ***
## TPeople 0.1549180 0.0108195 14.318 < 2e-16 ***
## TFamily 0.0528648 0.0080785 6.544 6.07e-11 ***
## TNeighbourhood 0.1115485 0.0063911 17.454 < 2e-16 ***
## TKnow -0.0036830 0.0063590 -0.579 0.562478
## TMeet 0.0997853 0.0060364 16.531 < 2e-16 ***
## VFamily 0.0039000 0.0121003 0.322 0.747221
## VFriends 0.0258051 0.0061643 4.186 2.84e-05 ***
## VLeisure -0.0511128 0.0055679 -9.180 < 2e-16 ***
## VReligion -0.0026734 0.0042026 -0.636 0.524699
## HSatFin -0.0071512 0.0018571 -3.851 0.000118 ***
## HMedicine -0.0179458 0.0048055 -3.734 0.000188 ***
## EPrivate -0.0071900 0.0015143 -4.748 2.06e-06 ***
## ECompetition -0.0046951 0.0016360 -2.870 0.004110 **
## EHardWork 0.0061514 0.0015081 4.079 4.53e-05 ***
## PIAB 0.0064109 0.0038892 1.648 0.099284 .
## STOpportunity -0.0107299 0.0018646 -5.755 8.75e-09 ***
## STFaith 0.0006943 0.0014781 0.470 0.638545
## STImportant 0.0088916 0.0014934 5.954 2.64e-09 ***
## PNewspaper 0.0243826 0.0028200 8.646 < 2e-16 ***
## PMobile 0.0214074 0.0030653 6.984 2.92e-12 ***
## PEmail -0.0194924 0.0031182 -6.251 4.12e-10 ***
## PSocial -0.0049811 0.0031017 -1.606 0.108303
## PDemImp 0.0148856 0.0020737 7.178 7.20e-13 ***
## PDemCurrent -0.0218543 0.0020666 -10.575 < 2e-16 ***
## PSatisfied -0.0971143 0.0019719 -49.249 < 2e-16 ***
## MF -0.0247179 0.0085068 -2.906 0.003667 **
## Age 0.0023192 0.0002908 7.974 1.58e-15 ***
## Edu 0.0351360 0.0023335 15.057 < 2e-16 ***
## Employment 0.0017558 0.0020976 0.837 0.402573
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8053 on 37425 degrees of freedom
## (11870 observations deleted due to missingness)
## Multiple R-squared: 0.2017, Adjusted R-squared: 0.2011
## F-statistic: 326.1 on 29 and 37425 DF, p-value: < 2.2e-16CParliament Regression Model
parliament_fit1 <-lm(paste("CParliament ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(parliament_fit1)##
## Call:
## lm(formula = paste("CParliament ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.0699 -0.5570 0.0258 0.5944 2.6969
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4605742 0.0511954 48.062 < 2e-16 ***
## TPeople 0.1372536 0.0111821 12.274 < 2e-16 ***
## TFamily 0.0761690 0.0083695 9.101 < 2e-16 ***
## TNeighbourhood 0.1188440 0.0066034 17.997 < 2e-16 ***
## TKnow 0.0217232 0.0065757 3.304 0.000956 ***
## TMeet 0.0726331 0.0062473 11.626 < 2e-16 ***
## VFamily 0.0256773 0.0125195 2.051 0.040276 *
## VFriends 0.0264293 0.0063749 4.146 3.39e-05 ***
## VLeisure -0.0733440 0.0057527 -12.750 < 2e-16 ***
## VReligion 0.0169512 0.0043452 3.901 9.59e-05 ***
## HSatFin -0.0047803 0.0019207 -2.489 0.012819 *
## HMedicine -0.0066144 0.0049704 -1.331 0.183273
## EPrivate -0.0071121 0.0015656 -4.543 5.57e-06 ***
## ECompetition -0.0025141 0.0016908 -1.487 0.137059
## EHardWork 0.0107800 0.0015584 6.918 4.67e-12 ***
## PIAB -0.0011882 0.0040210 -0.296 0.767613
## STOpportunity -0.0136740 0.0019285 -7.091 1.36e-12 ***
## STFaith 0.0085475 0.0015268 5.598 2.18e-08 ***
## STImportant 0.0123821 0.0015425 8.027 1.03e-15 ***
## PNewspaper 0.0305232 0.0029140 10.475 < 2e-16 ***
## PMobile 0.0247284 0.0031659 7.811 5.82e-15 ***
## PEmail -0.0182465 0.0032199 -5.667 1.46e-08 ***
## PSocial -0.0169188 0.0032039 -5.281 1.29e-07 ***
## PDemImp 0.0068491 0.0021442 3.194 0.001403 **
## PDemCurrent -0.0357470 0.0021376 -16.723 < 2e-16 ***
## PSatisfied -0.1075365 0.0020387 -52.747 < 2e-16 ***
## MF -0.0124910 0.0087918 -1.421 0.155397
## Age 0.0031255 0.0003006 10.397 < 2e-16 ***
## Edu 0.0279792 0.0024125 11.598 < 2e-16 ***
## Employment -0.0028275 0.0021679 -1.304 0.192157
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8324 on 37443 degrees of freedom
## (11852 observations deleted due to missingness)
## Multiple R-squared: 0.2331, Adjusted R-squared: 0.2325
## F-statistic: 392.5 on 29 and 37443 DF, p-value: < 2.2e-16CCivilservice Regression Model
civilService_fit1 <-lm(paste("CCivilService ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(civilService_fit1)##
## Call:
## lm(formula = paste("CCivilService ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.68310 -0.53522 -0.04386 0.56213 2.70629
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.0646250 0.0496034 41.623 < 2e-16 ***
## TPeople 0.1065775 0.0108187 9.851 < 2e-16 ***
## TFamily 0.0814748 0.0081009 10.057 < 2e-16 ***
## TNeighbourhood 0.1251903 0.0063978 19.568 < 2e-16 ***
## TKnow 0.0710298 0.0063698 11.151 < 2e-16 ***
## TMeet 0.0624669 0.0060448 10.334 < 2e-16 ***
## VFamily 0.0296303 0.0120893 2.451 0.014253 *
## VFriends 0.0377155 0.0061758 6.107 1.03e-09 ***
## VLeisure -0.0583793 0.0055811 -10.460 < 2e-16 ***
## VReligion 0.0295541 0.0042056 7.027 2.14e-12 ***
## HSatFin -0.0017552 0.0018595 -0.944 0.345212
## HMedicine -0.0281608 0.0048151 -5.848 5.00e-09 ***
## EPrivate -0.0074817 0.0015169 -4.932 8.16e-07 ***
## ECompetition -0.0003192 0.0016363 -0.195 0.845347
## EHardWork 0.0073731 0.0015081 4.889 1.02e-06 ***
## PIAB 0.0086458 0.0038940 2.220 0.026404 *
## STOpportunity -0.0202937 0.0018682 -10.863 < 2e-16 ***
## STFaith 0.0158413 0.0014799 10.705 < 2e-16 ***
## STImportant 0.0123390 0.0014947 8.255 < 2e-16 ***
## PNewspaper 0.0095516 0.0028212 3.386 0.000711 ***
## PMobile 0.0247785 0.0030684 8.075 6.93e-16 ***
## PEmail -0.0135800 0.0031190 -4.354 1.34e-05 ***
## PSocial -0.0063287 0.0031068 -2.037 0.041649 *
## PDemImp 0.0027000 0.0020753 1.301 0.193253
## PDemCurrent -0.0311706 0.0020700 -15.058 < 2e-16 ***
## PSatisfied -0.0631067 0.0019734 -31.979 < 2e-16 ***
## MF -0.0219841 0.0085137 -2.582 0.009821 **
## Age 0.0012846 0.0002912 4.411 1.03e-05 ***
## Edu 0.0164163 0.0023356 7.029 2.12e-12 ***
## Employment 0.0057480 0.0020995 2.738 0.006188 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.806 on 37428 degrees of freedom
## (11867 observations deleted due to missingness)
## Multiple R-squared: 0.1702, Adjusted R-squared: 0.1696
## F-statistic: 264.8 on 29 and 37428 DF, p-value: < 2.2e-16CElections Regression Model
elections_fit1 <-lm(paste("CElections ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(elections_fit1)##
## Call:
## lm(formula = paste("CElections ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.74178 -0.57198 -0.00728 0.61101 2.65978
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.537e+00 5.214e-02 48.653 < 2e-16 ***
## TPeople 9.740e-02 1.139e-02 8.552 < 2e-16 ***
## TFamily 5.210e-02 8.518e-03 6.116 9.68e-10 ***
## TNeighbourhood 9.678e-02 6.723e-03 14.396 < 2e-16 ***
## TKnow 5.872e-02 6.693e-03 8.773 < 2e-16 ***
## TMeet 7.764e-02 6.358e-03 12.212 < 2e-16 ***
## VFamily 6.358e-03 1.273e-02 0.500 0.617412
## VFriends 6.994e-03 6.484e-03 1.079 0.280754
## VLeisure -2.812e-02 5.863e-03 -4.796 1.63e-06 ***
## VReligion 2.662e-02 4.428e-03 6.013 1.84e-09 ***
## HSatFin -1.223e-02 1.954e-03 -6.257 3.97e-10 ***
## HMedicine -2.376e-02 5.059e-03 -4.697 2.65e-06 ***
## EPrivate -5.834e-03 1.593e-03 -3.662 0.000250 ***
## ECompetition 1.922e-03 1.720e-03 1.118 0.263780
## EHardWork 5.267e-03 1.585e-03 3.322 0.000893 ***
## PIAB -4.998e-03 4.093e-03 -1.221 0.222039
## STOpportunity -1.019e-02 1.963e-03 -5.191 2.10e-07 ***
## STFaith 1.777e-02 1.555e-03 11.430 < 2e-16 ***
## STImportant 7.326e-03 1.571e-03 4.662 3.14e-06 ***
## PNewspaper 3.482e-02 2.970e-03 11.723 < 2e-16 ***
## PMobile 2.084e-02 3.225e-03 6.463 1.04e-10 ***
## PEmail -4.279e-03 3.282e-03 -1.304 0.192316
## PSocial -3.612e-02 3.264e-03 -11.065 < 2e-16 ***
## PDemImp -4.191e-03 2.184e-03 -1.919 0.054945 .
## PDemCurrent -5.185e-02 2.174e-03 -23.854 < 2e-16 ***
## PSatisfied -7.920e-02 2.074e-03 -38.186 < 2e-16 ***
## MF 2.738e-02 8.956e-03 3.057 0.002236 **
## Age -2.105e-05 3.062e-04 -0.069 0.945192
## Edu 7.523e-03 2.456e-03 3.063 0.002191 **
## Employment -2.445e-03 2.208e-03 -1.107 0.268107
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8489 on 37539 degrees of freedom
## (11756 observations deleted due to missingness)
## Multiple R-squared: 0.2023, Adjusted R-squared: 0.2017
## F-statistic: 328.4 on 29 and 37539 DF, p-value: < 2.2e-16CEnvOrg Regression Model
envOrg_fit1 <-lm(paste("CEnvOrg ~", paste(predictors, collapse = " + ")), data = OtherCountriesData)
summary(envOrg_fit1)##
## Call:
## lm(formula = paste("CEnvOrg ~", paste(predictors, collapse = " + ")),
## data = OtherCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.3753 -0.4935 -0.1447 0.5987 2.4425
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.9259603 0.0522292 36.875 < 2e-16 ***
## TPeople 0.0362593 0.0114021 3.180 0.001474 **
## TFamily 0.0427891 0.0085068 5.030 4.93e-07 ***
## TNeighbourhood 0.0461439 0.0067344 6.852 7.40e-12 ***
## TKnow 0.0921628 0.0067015 13.753 < 2e-16 ***
## TMeet 0.0644677 0.0063716 10.118 < 2e-16 ***
## VFamily 0.0123119 0.0126803 0.971 0.331580
## VFriends 0.0070642 0.0065141 1.084 0.278174
## VLeisure 0.0147078 0.0058912 2.497 0.012545 *
## VReligion 0.0226768 0.0044291 5.120 3.07e-07 ***
## HSatFin -0.0122703 0.0019607 -6.258 3.94e-10 ***
## HMedicine 0.0126856 0.0050699 2.502 0.012350 *
## EPrivate -0.0122745 0.0016019 -7.662 1.87e-14 ***
## ECompetition -0.0030567 0.0017278 -1.769 0.076878 .
## EHardWork 0.0127929 0.0015929 8.031 9.94e-16 ***
## PIAB -0.0044143 0.0040993 -1.077 0.281559
## STOpportunity -0.0160351 0.0019678 -8.149 3.79e-16 ***
## STFaith 0.0076186 0.0015595 4.885 1.04e-06 ***
## STImportant 0.0118278 0.0015770 7.500 6.53e-14 ***
## PNewspaper 0.0242427 0.0029757 8.147 3.85e-16 ***
## PMobile 0.0232832 0.0032422 7.181 7.04e-13 ***
## PEmail -0.0119354 0.0032805 -3.638 0.000275 ***
## PSocial -0.0026019 0.0032726 -0.795 0.426583
## PDemImp -0.0206731 0.0021909 -9.436 < 2e-16 ***
## PDemCurrent -0.0221262 0.0021796 -10.151 < 2e-16 ***
## PSatisfied -0.0258636 0.0020777 -12.448 < 2e-16 ***
## MF -0.0417786 0.0089737 -4.656 3.24e-06 ***
## Age 0.0043046 0.0003066 14.039 < 2e-16 ***
## Edu 0.0235489 0.0024571 9.584 < 2e-16 ***
## Employment -0.0060407 0.0022090 -2.735 0.006250 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.84 on 36573 degrees of freedom
## (12722 observations deleted due to missingness)
## Multiple R-squared: 0.07992, Adjusted R-squared: 0.07919
## F-statistic: 109.5 on 29 and 36573 DF, p-value: < 2.2e-16Q3 Clustering
Q3 (a)
set.seed(9999)
ED <- read.csv("q3_external.csv", header = TRUE)
EDS <- ED
EDS[,2:6] <- scale(ED[,2:6])
library(cluster)create function to calculate average silhouette score
i_silhouette_score <- function(k){
km <- kmeans(EDS[,2:6], centers = k, nstart = 20)
ss <- silhouette(km$cluster, dist(EDS[,2:6]))
mean(ss[,3])
}determine optimal number of groups
k <- 2:10
avg_sil <- sapply(k, i_silhouette_score)
plot(k, type= 'b', avg_sil, xlab = 'Number of clusters', ylab = 'Average Silhouette Scores')
perform kmeans clustering
EDSkfit <- kmeans(EDS[,2:6],2, nstart = 20)
#EDSkfit
table(actual= EDS$Country, fitted= EDSkfit$cluster)## fitted
## actual 1 2
## Afghanistan 1 0
## Albania 1 0
## Algeria 1 0
## Angola 1 0
## Antigua and Barbuda 1 0
## Argentina 0 1
## Armenia 0 1
## Australia 0 1
## Austria 0 1
## Azerbaijan 1 0
## Bahamas 0 1
## Bahrain 0 1
## Bangladesh 1 0
## Barbados 0 1
## Belarus 1 0
## Belgium 0 1
## Belize 1 0
## Benin 1 0
## Bhutan 1 0
## Bolivia 1 0
## Bosnia and Herzegovina 1 0
## Botswana 1 0
## Brazil 0 1
## Brunei Darussalam 0 1
## Bulgaria 0 1
## Burkina Faso 1 0
## Burundi 1 0
## Cabo Verde 1 0
## Cambodia 1 0
## Cameroon 1 0
## Canada 0 1
## Central African Republic 1 0
## Chad 1 0
## Chile 0 1
## China 0 1
## Colombia 0 1
## Comoros 1 0
## Congo 1 0
## Costa Rica 0 1
## Côte d'Ivoire 1 0
## Croatia 0 1
## Cuba 1 0
## Cyprus 0 1
## Czechia 0 1
## Denmark 0 1
## Djibouti 1 0
## Dominican Republic 1 0
## Ecuador 0 1
## Egypt 1 0
## El Salvador 1 0
## Equatorial Guinea 1 0
## Eritrea 1 0
## Estonia 0 1
## Eswatini 1 0
## Ethiopia 1 0
## Fiji 1 0
## Finland 0 1
## France 0 1
## Gabon 1 0
## Gambia 1 0
## Georgia 0 1
## Germany 0 1
## Ghana 1 0
## Greece 0 1
## Grenada 1 0
## Guatemala 1 0
## Guinea 1 0
## Guinea-Bissau 1 0
## Guyana 1 0
## Haiti 1 0
## Honduras 1 0
## Hungary 0 1
## Iceland 0 1
## India 1 0
## Indonesia 1 0
## Iran 1 0
## Iraq 1 0
## Ireland 0 1
## Israel 0 1
## Italy 0 1
## Jamaica 1 0
## Japan 0 1
## Jordan 1 0
## Kazakhstan 0 1
## Kenya 1 0
## Kiribati 1 0
## Kuwait 0 1
## Kyrgyzstan 1 0
## Laos 1 0
## Latvia 0 1
## Lebanon 1 0
## Lesotho 1 0
## Liberia 1 0
## Libya 1 0
## Lithuania 0 1
## Luxembourg 0 1
## Madagascar 1 0
## Malawi 1 0
## Malaysia 0 1
## Maldives 1 0
## Mali 1 0
## Malta 0 1
## Mauritania 1 0
## Mauritius 1 0
## Mexico 0 1
## Moldova 1 0
## Mongolia 1 0
## Montenegro 1 0
## Morocco 1 0
## Mozambique 1 0
## Myanmar 1 0
## Namibia 1 0
## Nepal 1 0
## Netherlands 0 1
## New Zealand 0 1
## Nicaragua 1 0
## Niger 1 0
## Nigeria 1 0
## North Korea 1 0
## North Macedonia 1 0
## Norway 0 1
## Oman 1 0
## Pakistan 1 0
## Panama 0 1
## Papua New Guinea 1 0
## Paraguay 1 0
## Peru 0 1
## Philippines 1 0
## Poland 0 1
## Portugal 0 1
## Qatar 0 1
## Romania 0 1
## Russia 0 1
## Rwanda 1 0
## Samoa 1 0
## Sao Tome and Principe 1 0
## Saudi Arabia 0 1
## Senegal 1 0
## Serbia 1 0
## Seychelles 0 1
## Sierra Leone 1 0
## Singapore 0 1
## Slovakia 0 1
## Slovenia 0 1
## Solomon Islands 1 0
## Somalia 1 0
## South Africa 1 0
## South Korea 0 1
## South Sudan 1 0
## Spain 0 1
## Sri Lanka 1 0
## Sudan 1 0
## Suriname 1 0
## Sweden 0 1
## Switzerland 0 1
## Syrian Arab Republic 1 0
## Tajikistan 1 0
## Tanzania 1 0
## Thailand 0 1
## Timor-Leste 1 0
## Togo 1 0
## Tonga 1 0
## Trinidad and Tobago 0 1
## Tunisia 1 0
## Turkey 0 1
## Turkmenistan 1 0
## Uganda 1 0
## Ukraine 1 0
## United Arab Emirates 0 1
## United Kingdom 0 1
## United States of America 0 1
## Uruguay 0 1
## Uzbekistan 1 0
## Vanuatu 1 0
## Venezuela 1 0
## Viet Nam 0 1
## Yemen 1 0
## Zambia 1 0
## Zimbabwe 1 0ED$cluster <- EDSkfit$cluster
#View(ED)countries similar to Malaysia
malaysia_cluster <- ED[ED$Country == "Malaysia", "cluster"]
similar_countries_cluster <- ED[which(ED$cluster == malaysia_cluster),]
print(similar_countries_cluster$Country)## [1] "Argentina" "Armenia"
## [3] "Australia" "Austria"
## [5] "Bahamas" "Bahrain"
## [7] "Barbados" "Belgium"
## [9] "Brazil" "Brunei Darussalam"
## [11] "Bulgaria" "Canada"
## [13] "Chile" "China"
## [15] "Colombia" "Costa Rica"
## [17] "Croatia" "Cyprus"
## [19] "Czechia" "Denmark"
## [21] "Ecuador" "Estonia"
## [23] "Finland" "France"
## [25] "Georgia" "Germany"
## [27] "Greece" "Hungary"
## [29] "Iceland" "Ireland"
## [31] "Israel" "Italy"
## [33] "Japan" "Kazakhstan"
## [35] "Kuwait" "Latvia"
## [37] "Lithuania" "Luxembourg"
## [39] "Malaysia" "Malta"
## [41] "Mexico" "Netherlands"
## [43] "New Zealand" "Norway"
## [45] "Panama" "Peru"
## [47] "Poland" "Portugal"
## [49] "Qatar" "South Korea"
## [51] "Romania" "Russia"
## [53] "Saudi Arabia" "Seychelles"
## [55] "Singapore" "Slovakia"
## [57] "Slovenia" "Spain"
## [59] "Sweden" "Switzerland"
## [61] "Thailand" "Trinidad and Tobago"
## [63] "Turkey" "United Arab Emirates"
## [65] "United Kingdom" "United States of America"
## [67] "Uruguay" "Viet Nam"#create cluster plot
rownames(EDS) <- ED$Country
fviz_cluster(EDSkfit, data = EDS[,2:6],
palette=c("red", "blue"),
ellipse.type = "euclid",
star.plot = T,
repel = T,
ggtheme = theme())
find unique countries in VCData
unique(VCData$Country)## [1] "CAN" "MEX" "PAK" "NGA" "BGD" "RUS" "IDN" "USA" "PHL" "DEU" "AND" "BOL"
## [13] "NLD" "MAC" "MNG" "CHN" "ARM" "ZWE" "UKR" "AUS" "IND" "LBY" "NZL" "KAZ"
## [25] "TUR" "SVK" "CYP" "TJK" "COL" "IRN" "VNM" "UZB" "TUN" "BRA" "GBR" "CZE"
## [37] "MMR" "SRB" "GRC" "LBN" "GTM" "IRQ" "PER" "KGZ" "KEN" "THA" "KOR" "PRI"
## [49] "SGP" "HKG" "MYS" "EGY" "CHL" "MAR" "ECU" "VEN" "ROU" "JPN" "MDV" "NIC"
## [61] "ARG" "TWN" "JOR" "URY" "ETH"Q3 (b)
filter dataset to include only cluster countries
ClusterCountries <- c("ARG", "ARM", "AUS", "BRA", "CAN", "CHL", "CHN", "COL", "CYP", "CZE",
"ECU", "DEU", "GRC", "JPN", "KAZ", "MEX", "NLD", "NZL", "PER",
"ROU", "RUS", "SGP", "SVK", "KOR", "THA", "TUR", "GBR", "USA", "URY", "VNM")
ClusterCountriesData <- CombinedData %>% filter(Country %in% ClusterCountries)
ClusterCountriesData$Group <- NULL
#View(ClusterCountriesData)Finding the best predictors for CLUSTER COUNTRIES
CReligious Regression Model
religious_fit2 <-lm(paste("CReligious ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(religious_fit2)##
## Call:
## lm(formula = paste("CReligious ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.54583 -0.58496 -0.01565 0.51228 2.69236
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.1761934 0.0712525 16.507 < 2e-16 ***
## TPeople 0.0322257 0.0139695 2.307 0.02107 *
## TFamily 0.1061138 0.0110980 9.562 < 2e-16 ***
## TNeighbourhood 0.1104760 0.0092462 11.948 < 2e-16 ***
## TKnow -0.0029553 0.0093824 -0.315 0.75278
## TMeet 0.0396751 0.0087941 4.512 6.47e-06 ***
## VFamily 0.0392182 0.0151658 2.586 0.00972 **
## VFriends -0.0380177 0.0087226 -4.359 1.32e-05 ***
## VLeisure -0.0530996 0.0082885 -6.406 1.52e-10 ***
## VReligion 0.4397484 0.0055477 79.267 < 2e-16 ***
## HSatFin -0.0086220 0.0027008 -3.192 0.00141 **
## HMedicine 0.0019499 0.0073291 0.266 0.79021
## EPrivate 0.0007071 0.0022520 0.314 0.75354
## ECompetition -0.0031231 0.0024707 -1.264 0.20623
## EHardWork 0.0149439 0.0021854 6.838 8.27e-12 ***
## PIAB -0.0127858 0.0052819 -2.421 0.01550 *
## STOpportunity -0.0038602 0.0026150 -1.476 0.13991
## STFaith -0.0122099 0.0021145 -5.775 7.84e-09 ***
## STImportant -0.0174129 0.0021213 -8.208 2.38e-16 ***
## PNewspaper 0.0147102 0.0037264 3.948 7.92e-05 ***
## PMobile -0.0052281 0.0043053 -1.214 0.22463
## PEmail -0.0092228 0.0040669 -2.268 0.02335 *
## PSocial -0.0138346 0.0042588 -3.249 0.00116 **
## PDemImp 0.0161737 0.0030831 5.246 1.57e-07 ***
## PDemCurrent -0.0038406 0.0030188 -1.272 0.20331
## PSatisfied -0.0236360 0.0028072 -8.420 < 2e-16 ***
## MF -0.0486136 0.0115735 -4.200 2.68e-05 ***
## Age 0.0019484 0.0004007 4.863 1.17e-06 ***
## Edu 0.0081634 0.0032163 2.538 0.01115 *
## Employment -0.0070537 0.0028934 -2.438 0.01478 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7784 on 19060 degrees of freedom
## (6386 observations deleted due to missingness)
## Multiple R-squared: 0.3223, Adjusted R-squared: 0.3212
## F-statistic: 312.5 on 29 and 19060 DF, p-value: < 2.2e-16CPress Regression Model
press_fit2 <-lm(paste("CPress ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(press_fit2)##
## Call:
## lm(formula = paste("CPress ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.55568 -0.53787 0.03502 0.52172 2.16818
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2691731 0.0700846 32.378 < 2e-16 ***
## TPeople 0.1322409 0.0136975 9.654 < 2e-16 ***
## TFamily 0.0595585 0.0109096 5.459 4.84e-08 ***
## TNeighbourhood 0.1234149 0.0090860 13.583 < 2e-16 ***
## TKnow -0.0216410 0.0092254 -2.346 0.018995 *
## TMeet 0.0771256 0.0086438 8.923 < 2e-16 ***
## VFamily 0.0025041 0.0148950 0.168 0.866491
## VFriends -0.0050908 0.0085796 -0.593 0.552948
## VLeisure -0.0290420 0.0081426 -3.567 0.000362 ***
## VReligion -0.0017159 0.0054408 -0.315 0.752481
## HSatFin -0.0069011 0.0026554 -2.599 0.009360 **
## HMedicine -0.0003295 0.0072115 -0.046 0.963561
## EPrivate -0.0046898 0.0022147 -2.118 0.034227 *
## ECompetition -0.0073477 0.0024278 -3.026 0.002477 **
## EHardWork 0.0075460 0.0021481 3.513 0.000444 ***
## PIAB -0.0114822 0.0051839 -2.215 0.026775 *
## STOpportunity -0.0213710 0.0025671 -8.325 < 2e-16 ***
## STFaith 0.0061760 0.0020748 2.977 0.002917 **
## STImportant 0.0051852 0.0020837 2.488 0.012838 *
## PNewspaper 0.0565323 0.0036531 15.475 < 2e-16 ***
## PMobile 0.0116193 0.0042232 2.751 0.005942 **
## PEmail 0.0017292 0.0039885 0.434 0.664629
## PSocial -0.0127841 0.0041766 -3.061 0.002210 **
## PDemImp 0.0184911 0.0030302 6.102 1.07e-09 ***
## PDemCurrent -0.0162619 0.0029707 -5.474 4.45e-08 ***
## PSatisfied -0.0616288 0.0027611 -22.320 < 2e-16 ***
## MF -0.0146571 0.0113582 -1.290 0.196914
## Age -0.0000148 0.0003934 -0.038 0.969990
## Edu 0.0232867 0.0031572 7.376 1.70e-13 ***
## Employment -0.0015516 0.0028422 -0.546 0.585131
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7656 on 19136 degrees of freedom
## (6310 observations deleted due to missingness)
## Multiple R-squared: 0.1492, Adjusted R-squared: 0.1479
## F-statistic: 115.7 on 29 and 19136 DF, p-value: < 2.2e-16CTelevision Regression Model
television_fit2 <-lm(paste("CTelevision ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(television_fit2)##
## Call:
## lm(formula = paste("CTelevision ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.50890 -0.51909 0.02971 0.50489 2.11937
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3047779 0.0680719 33.858 < 2e-16 ***
## TPeople 0.0843542 0.0133156 6.335 2.43e-10 ***
## TFamily 0.0749011 0.0106133 7.057 1.76e-12 ***
## TNeighbourhood 0.1197881 0.0088248 13.574 < 2e-16 ***
## TKnow -0.0035554 0.0089611 -0.397 0.691551
## TMeet 0.0553652 0.0083960 6.594 4.39e-11 ***
## VFamily 0.0108970 0.0145030 0.751 0.452444
## VFriends 0.0004292 0.0083305 0.052 0.958910
## VLeisure -0.0272047 0.0079064 -3.441 0.000581 ***
## VReligion -0.0015982 0.0052905 -0.302 0.762584
## HSatFin -0.0061466 0.0025807 -2.382 0.017239 *
## HMedicine -0.0012646 0.0070090 -0.180 0.856821
## EPrivate -0.0055837 0.0021516 -2.595 0.009462 **
## ECompetition -0.0054399 0.0023591 -2.306 0.021128 *
## EHardWork 0.0105431 0.0020872 5.051 4.43e-07 ***
## PIAB -0.0086883 0.0050401 -1.724 0.084753 .
## STOpportunity -0.0180053 0.0024944 -7.218 5.46e-13 ***
## STFaith 0.0030921 0.0020181 1.532 0.125503
## STImportant -0.0015464 0.0020241 -0.764 0.444868
## PNewspaper 0.0430018 0.0035542 12.099 < 2e-16 ***
## PMobile 0.0192633 0.0041050 4.693 2.72e-06 ***
## PEmail -0.0095552 0.0038851 -2.459 0.013924 *
## PSocial -0.0062877 0.0040628 -1.548 0.121731
## PDemImp 0.0270263 0.0029417 9.187 < 2e-16 ***
## PDemCurrent -0.0150920 0.0028863 -5.229 1.72e-07 ***
## PSatisfied -0.0667465 0.0026823 -24.884 < 2e-16 ***
## MF -0.0602095 0.0110424 -5.453 5.03e-08 ***
## Age -0.0005919 0.0003823 -1.548 0.121581
## Edu 0.0425865 0.0030676 13.883 < 2e-16 ***
## Employment 0.0017832 0.0027627 0.645 0.518639
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7455 on 19196 degrees of freedom
## (6250 observations deleted due to missingness)
## Multiple R-squared: 0.1519, Adjusted R-squared: 0.1506
## F-statistic: 118.5 on 29 and 19196 DF, p-value: < 2.2e-16CUnions Regression Model
unions_fit2 <-lm(paste("CUnions ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(unions_fit2)##
## Call:
## lm(formula = paste("CUnions ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.68680 -0.55524 0.04165 0.53219 2.12814
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.0494521 0.0726543 28.208 < 2e-16 ***
## TPeople 0.1274032 0.0142086 8.967 < 2e-16 ***
## TFamily 0.0656061 0.0112728 5.820 5.99e-09 ***
## TNeighbourhood 0.1025118 0.0094460 10.852 < 2e-16 ***
## TKnow 0.0540421 0.0095769 5.643 1.70e-08 ***
## TMeet 0.1012732 0.0089984 11.255 < 2e-16 ***
## VFamily -0.0073202 0.0154233 -0.475 0.635065
## VFriends 0.0400002 0.0089124 4.488 7.23e-06 ***
## VLeisure -0.0310266 0.0084889 -3.655 0.000258 ***
## VReligion -0.0267813 0.0056657 -4.727 2.30e-06 ***
## HSatFin 0.0020994 0.0027658 0.759 0.447816
## HMedicine -0.0133589 0.0074778 -1.786 0.074038 .
## EPrivate -0.0193189 0.0023099 -8.364 < 2e-16 ***
## ECompetition -0.0130539 0.0025313 -5.157 2.53e-07 ***
## EHardWork 0.0066405 0.0022392 2.966 0.003025 **
## PIAB 0.0004356 0.0053946 0.081 0.935638
## STOpportunity -0.0141016 0.0026652 -5.291 1.23e-07 ***
## STFaith 0.0068331 0.0021611 3.162 0.001570 **
## STImportant 0.0067258 0.0021753 3.092 0.001992 **
## PNewspaper 0.0328075 0.0038033 8.626 < 2e-16 ***
## PMobile 0.0223323 0.0044077 5.067 4.09e-07 ***
## PEmail -0.0153554 0.0041433 -3.706 0.000211 ***
## PSocial 0.0106467 0.0043512 2.447 0.014422 *
## PDemImp 0.0068868 0.0031468 2.189 0.028645 *
## PDemCurrent -0.0071974 0.0030806 -2.336 0.019484 *
## PSatisfied -0.0461116 0.0028630 -16.106 < 2e-16 ***
## MF -0.0643364 0.0118028 -5.451 5.07e-08 ***
## Age 0.0019973 0.0004100 4.872 1.11e-06 ***
## Edu 0.0179176 0.0032801 5.463 4.75e-08 ***
## Employment 0.0069688 0.0029519 2.361 0.018249 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7815 on 18443 degrees of freedom
## (7003 observations deleted due to missingness)
## Multiple R-squared: 0.1345, Adjusted R-squared: 0.1332
## F-statistic: 98.86 on 29 and 18443 DF, p-value: < 2.2e-16CCourts Regression Model
courts_fit2 <-lm(paste("CCourts ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(courts_fit2)##
## Call:
## lm(formula = paste("CCourts ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.73393 -0.52403 -0.04758 0.55818 2.51880
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.9959774 0.0732911 27.234 < 2e-16 ***
## TPeople 0.1630897 0.0143083 11.398 < 2e-16 ***
## TFamily 0.0873433 0.0114072 7.657 2.00e-14 ***
## TNeighbourhood 0.1158712 0.0094974 12.200 < 2e-16 ***
## TKnow 0.1040286 0.0096409 10.790 < 2e-16 ***
## TMeet 0.0319911 0.0090369 3.540 0.000401 ***
## VFamily 0.0104735 0.0155894 0.672 0.501700
## VFriends 0.0574147 0.0089739 6.398 1.61e-10 ***
## VLeisure -0.0579654 0.0085106 -6.811 9.98e-12 ***
## VReligion 0.0092364 0.0056917 1.623 0.104655
## HSatFin -0.0088992 0.0027762 -3.206 0.001350 **
## HMedicine -0.0745899 0.0075407 -9.892 < 2e-16 ***
## EPrivate 0.0055652 0.0023182 2.401 0.016378 *
## ECompetition -0.0015328 0.0025424 -0.603 0.546594
## EHardWork 0.0096956 0.0022497 4.310 1.64e-05 ***
## PIAB 0.0092143 0.0054208 1.700 0.089182 .
## STOpportunity -0.0161504 0.0026855 -6.014 1.84e-09 ***
## STFaith 0.0185850 0.0021709 8.561 < 2e-16 ***
## STImportant 0.0101866 0.0021813 4.670 3.03e-06 ***
## PNewspaper 0.0103560 0.0038213 2.710 0.006733 **
## PMobile 0.0233043 0.0044195 5.273 1.36e-07 ***
## PEmail -0.0032531 0.0041687 -0.780 0.435196
## PSocial -0.0033385 0.0043653 -0.765 0.444416
## PDemImp 0.0091748 0.0031661 2.898 0.003762 **
## PDemCurrent -0.0264925 0.0031057 -8.530 < 2e-16 ***
## PSatisfied -0.0657661 0.0028870 -22.780 < 2e-16 ***
## MF -0.0181360 0.0118716 -1.528 0.126610
## Age -0.0001053 0.0004117 -0.256 0.798054
## Edu 0.0134099 0.0032974 4.067 4.78e-05 ***
## Employment 0.0027528 0.0029695 0.927 0.353927
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7984 on 19048 degrees of freedom
## (6398 observations deleted due to missingness)
## Multiple R-squared: 0.2048, Adjusted R-squared: 0.2036
## F-statistic: 169.1 on 29 and 19048 DF, p-value: < 2.2e-16CPParties Regression Model
pparties_fit2 <-lm(paste("CPParties ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(pparties_fit2)##
## Call:
## lm(formula = paste("CPParties ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.14174 -0.49995 0.06452 0.51573 2.26558
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3915197 0.0689638 34.678 < 2e-16 ***
## TPeople 0.2026132 0.0134871 15.023 < 2e-16 ***
## TFamily 0.0730319 0.0107332 6.804 1.05e-11 ***
## TNeighbourhood 0.1214502 0.0089349 13.593 < 2e-16 ***
## TKnow 0.0139288 0.0090757 1.535 0.124866
## TMeet 0.0681373 0.0085038 8.013 1.19e-15 ***
## VFamily 0.0102197 0.0146426 0.698 0.485221
## VFriends 0.0320656 0.0084315 3.803 0.000143 ***
## VLeisure -0.0775121 0.0079998 -9.689 < 2e-16 ***
## VReligion -0.0053848 0.0053578 -1.005 0.314895
## HSatFin -0.0072237 0.0026105 -2.767 0.005661 **
## HMedicine -0.0111225 0.0070904 -1.569 0.116739
## EPrivate -0.0085828 0.0021790 -3.939 8.21e-05 ***
## ECompetition -0.0086100 0.0023918 -3.600 0.000319 ***
## EHardWork 0.0123578 0.0021152 5.842 5.23e-09 ***
## PIAB 0.0118645 0.0051064 2.323 0.020164 *
## STOpportunity -0.0199979 0.0025251 -7.920 2.51e-15 ***
## STFaith -0.0069655 0.0020440 -3.408 0.000656 ***
## STImportant 0.0193494 0.0020503 9.437 < 2e-16 ***
## PNewspaper 0.0163469 0.0035994 4.542 5.62e-06 ***
## PMobile 0.0258871 0.0041548 6.231 4.74e-10 ***
## PEmail -0.0275519 0.0039278 -7.015 2.38e-12 ***
## PSocial 0.0191849 0.0041095 4.668 3.06e-06 ***
## PDemImp 0.0263261 0.0029809 8.832 < 2e-16 ***
## PDemCurrent -0.0067538 0.0029187 -2.314 0.020678 *
## PSatisfied -0.1111140 0.0027136 -40.948 < 2e-16 ***
## MF -0.0244805 0.0111809 -2.189 0.028573 *
## Age 0.0018662 0.0003873 4.818 1.46e-06 ***
## Edu 0.0409648 0.0031080 13.180 < 2e-16 ***
## Employment -0.0008380 0.0027960 -0.300 0.764402
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7521 on 19062 degrees of freedom
## (6384 observations deleted due to missingness)
## Multiple R-squared: 0.2568, Adjusted R-squared: 0.2556
## F-statistic: 227.1 on 29 and 19062 DF, p-value: < 2.2e-16CParliament Regression Model
parliament_fit2 <-lm(paste("CParliament ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(parliament_fit2)##
## Call:
## lm(formula = paste("CParliament ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.98234 -0.50346 0.02038 0.53195 2.57863
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4695345 0.0702432 35.157 < 2e-16 ***
## TPeople 0.1865382 0.0137336 13.583 < 2e-16 ***
## TFamily 0.0750346 0.0109339 6.863 6.97e-12 ***
## TNeighbourhood 0.1167913 0.0091044 12.828 < 2e-16 ***
## TKnow 0.0406956 0.0092477 4.401 1.09e-05 ***
## TMeet 0.0609645 0.0086657 7.035 2.06e-12 ***
## VFamily 0.0231418 0.0149359 1.549 0.12130
## VFriends 0.0266446 0.0085905 3.102 0.00193 **
## VLeisure -0.0820433 0.0081511 -10.065 < 2e-16 ***
## VReligion 0.0061257 0.0054572 1.123 0.26166
## HSatFin -0.0034520 0.0026616 -1.297 0.19465
## HMedicine -0.0198125 0.0072179 -2.745 0.00606 **
## EPrivate -0.0094841 0.0022190 -4.274 1.93e-05 ***
## ECompetition -0.0048226 0.0024377 -1.978 0.04791 *
## EHardWork 0.0121235 0.0021554 5.625 1.88e-08 ***
## PIAB 0.0086338 0.0052015 1.660 0.09696 .
## STOpportunity -0.0209786 0.0025726 -8.155 3.71e-16 ***
## STFaith 0.0039165 0.0020805 1.882 0.05978 .
## STImportant 0.0199664 0.0020865 9.570 < 2e-16 ***
## PNewspaper 0.0172890 0.0036650 4.717 2.41e-06 ***
## PMobile 0.0174258 0.0042304 4.119 3.82e-05 ***
## PEmail -0.0220417 0.0039985 -5.513 3.58e-08 ***
## PSocial 0.0229316 0.0041852 5.479 4.33e-08 ***
## PDemImp 0.0201903 0.0030414 6.638 3.26e-11 ***
## PDemCurrent -0.0204379 0.0029761 -6.867 6.74e-12 ***
## PSatisfied -0.1264330 0.0027663 -45.704 < 2e-16 ***
## MF -0.0222685 0.0113844 -1.956 0.05047 .
## Age 0.0012231 0.0003943 3.102 0.00193 **
## Edu 0.0269764 0.0031647 8.524 < 2e-16 ***
## Employment 0.0003252 0.0028485 0.114 0.90912
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7652 on 19026 degrees of freedom
## (6420 observations deleted due to missingness)
## Multiple R-squared: 0.2955, Adjusted R-squared: 0.2944
## F-statistic: 275.2 on 29 and 19026 DF, p-value: < 2.2e-16CCivilService Regression Model
civilService_fit2 <-lm(paste("CCivilService ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(civilService_fit2)##
## Call:
## lm(formula = paste("CCivilService ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.76264 -0.48833 -0.05746 0.54176 2.34033
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.1524923 0.0689769 31.206 < 2e-16 ***
## TPeople 0.1408549 0.0134687 10.458 < 2e-16 ***
## TFamily 0.0749386 0.0107415 6.977 3.12e-12 ***
## TNeighbourhood 0.1101538 0.0089369 12.326 < 2e-16 ***
## TKnow 0.1159068 0.0090688 12.781 < 2e-16 ***
## TMeet 0.0550542 0.0084990 6.478 9.54e-11 ***
## VFamily 0.0180942 0.0146186 1.238 0.215822
## VFriends 0.0535308 0.0084351 6.346 2.26e-10 ***
## VLeisure -0.0690031 0.0080019 -8.623 < 2e-16 ***
## VReligion 0.0097332 0.0053553 1.817 0.069159 .
## HSatFin 0.0041785 0.0026117 1.600 0.109639
## HMedicine -0.0647370 0.0070879 -9.133 < 2e-16 ***
## EPrivate -0.0081832 0.0021783 -3.757 0.000173 ***
## ECompetition -0.0032871 0.0023884 -1.376 0.168760
## EHardWork 0.0038368 0.0021129 1.816 0.069410 .
## PIAB 0.0236871 0.0051073 4.638 3.54e-06 ***
## STOpportunity -0.0235750 0.0025247 -9.338 < 2e-16 ***
## STFaith 0.0115581 0.0020418 5.661 1.53e-08 ***
## STImportant 0.0130458 0.0020483 6.369 1.95e-10 ***
## PNewspaper -0.0043020 0.0035972 -1.196 0.231746
## PMobile 0.0163953 0.0041569 3.944 8.04e-05 ***
## PEmail -0.0146409 0.0039301 -3.725 0.000196 ***
## PSocial 0.0187948 0.0041149 4.568 4.97e-06 ***
## PDemImp 0.0135974 0.0029798 4.563 5.07e-06 ***
## PDemCurrent -0.0089293 0.0029204 -3.058 0.002235 **
## PSatisfied -0.0751402 0.0027128 -27.698 < 2e-16 ***
## MF -0.0310702 0.0111731 -2.781 0.005428 **
## Age -0.0004610 0.0003872 -1.191 0.233802
## Edu 0.0075626 0.0031028 2.437 0.014806 *
## Employment 0.0057487 0.0027943 2.057 0.039669 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7511 on 19031 degrees of freedom
## (6415 observations deleted due to missingness)
## Multiple R-squared: 0.2113, Adjusted R-squared: 0.2101
## F-statistic: 175.8 on 29 and 19031 DF, p-value: < 2.2e-16CElections Regression Model
elections_fit2 <-lm(paste("CElections ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(elections_fit2)##
## Call:
## lm(formula = paste("CElections ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.63741 -0.52204 -0.01926 0.56436 2.51336
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5457439 0.0725289 35.100 < 2e-16 ***
## TPeople 0.1207126 0.0141720 8.518 < 2e-16 ***
## TFamily 0.0601023 0.0112828 5.327 1.01e-07 ***
## TNeighbourhood 0.1064910 0.0093917 11.339 < 2e-16 ***
## TKnow 0.0994317 0.0095428 10.420 < 2e-16 ***
## TMeet 0.0766460 0.0089421 8.571 < 2e-16 ***
## VFamily 0.0056561 0.0153934 0.367 0.713296
## VFriends 0.0065462 0.0088611 0.739 0.460064
## VLeisure -0.0153524 0.0084161 -1.824 0.068141 .
## VReligion 0.0269983 0.0056317 4.794 1.65e-06 ***
## HSatFin -0.0041321 0.0027410 -1.508 0.131694
## HMedicine -0.0645674 0.0074588 -8.657 < 2e-16 ***
## EPrivate -0.0064070 0.0022910 -2.797 0.005170 **
## ECompetition 0.0012537 0.0025106 0.499 0.617524
## EHardWork 0.0027040 0.0022204 1.218 0.223315
## PIAB 0.0038169 0.0053654 0.711 0.476855
## STOpportunity -0.0087485 0.0026538 -3.297 0.000981 ***
## STFaith 0.0119297 0.0021460 5.559 2.75e-08 ***
## STImportant 0.0065785 0.0021535 3.055 0.002255 **
## PNewspaper 0.0306070 0.0037823 8.092 6.21e-16 ***
## PMobile 0.0208850 0.0043675 4.782 1.75e-06 ***
## PEmail -0.0058227 0.0041312 -1.409 0.158726
## PSocial -0.0118278 0.0043226 -2.736 0.006220 **
## PDemImp -0.0070557 0.0031319 -2.253 0.024280 *
## PDemCurrent -0.0489983 0.0030681 -15.970 < 2e-16 ***
## PSatisfied -0.0772403 0.0028521 -27.082 < 2e-16 ***
## MF 0.0370588 0.0117471 3.155 0.001609 **
## Age -0.0018971 0.0004074 -4.656 3.25e-06 ***
## Edu -0.0067826 0.0032638 -2.078 0.037711 *
## Employment -0.0050986 0.0029383 -1.735 0.082723 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.79 on 19041 degrees of freedom
## (6405 observations deleted due to missingness)
## Multiple R-squared: 0.2442, Adjusted R-squared: 0.2431
## F-statistic: 212.2 on 29 and 19041 DF, p-value: < 2.2e-16CEnvOrg Regression Model
envOrg_fit2 <-lm(paste("CEnvOrg ~", paste(predictors, collapse = " + ")), data = ClusterCountriesData)
summary(envOrg_fit2)##
## Call:
## lm(formula = paste("CEnvOrg ~", paste(predictors, collapse = " + ")),
## data = ClusterCountriesData)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4322 -0.4628 -0.1382 0.5652 2.3017
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.092e+00 7.342e-02 28.501 < 2e-16 ***
## TPeople 7.596e-02 1.436e-02 5.289 1.25e-07 ***
## TFamily 4.584e-02 1.140e-02 4.020 5.84e-05 ***
## TNeighbourhood 4.550e-02 9.525e-03 4.777 1.79e-06 ***
## TKnow 1.134e-01 9.687e-03 11.707 < 2e-16 ***
## TMeet 5.786e-02 9.082e-03 6.371 1.92e-10 ***
## VFamily 3.004e-03 1.552e-02 0.194 0.846486
## VFriends 9.053e-03 9.002e-03 1.006 0.314578
## VLeisure -1.142e-02 8.546e-03 -1.336 0.181435
## VReligion 2.716e-03 5.720e-03 0.475 0.634885
## HSatFin -1.231e-02 2.788e-03 -4.415 1.02e-05 ***
## HMedicine 1.066e-02 7.563e-03 1.410 0.158636
## EPrivate -1.836e-02 2.328e-03 -7.887 3.27e-15 ***
## ECompetition -6.230e-03 2.555e-03 -2.438 0.014779 *
## EHardWork 6.002e-03 2.258e-03 2.658 0.007860 **
## PIAB 7.522e-05 5.438e-03 0.014 0.988963
## STOpportunity -2.696e-02 2.692e-03 -10.013 < 2e-16 ***
## STFaith 7.560e-03 2.181e-03 3.466 0.000529 ***
## STImportant 1.371e-02 2.189e-03 6.262 3.88e-10 ***
## PNewspaper 1.600e-02 3.846e-03 4.160 3.20e-05 ***
## PMobile 2.044e-02 4.447e-03 4.597 4.32e-06 ***
## PEmail -1.158e-02 4.181e-03 -2.770 0.005615 **
## PSocial 7.625e-03 4.382e-03 1.740 0.081868 .
## PDemImp -1.553e-02 3.184e-03 -4.878 1.08e-06 ***
## PDemCurrent -1.203e-02 3.114e-03 -3.864 0.000112 ***
## PSatisfied -2.646e-02 2.891e-03 -9.153 < 2e-16 ***
## MF -6.715e-02 1.192e-02 -5.632 1.81e-08 ***
## Age 3.884e-03 4.130e-04 9.405 < 2e-16 ***
## Edu 1.448e-02 3.308e-03 4.376 1.21e-05 ***
## Employment -6.403e-03 2.975e-03 -2.153 0.031362 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7924 on 18586 degrees of freedom
## (6860 observations deleted due to missingness)
## Multiple R-squared: 0.09385, Adjusted R-squared: 0.09244
## F-statistic: 66.38 on 29 and 18586 DF, p-value: < 2.2e-16