Assignment 1 FIT 3152
Michael Gowanto
Student ID: 31225381
Set The Working Directory
# (1) set the current working directory
setwd("D:/Uni/Year 4 Sem 1/FIT3152/Assignment 1")Code Running for Covid-19 Data Analysis
rm(list = ls())
set.seed(31225381) # XXXXXXXX = your student ID
cvbase = read.csv("PsyCoronaBaselineExtract.csv")
cvbase <- cvbase[sample(nrow(cvbase), 40000), ] # 40000 rowsLibrary Package Access
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.2.3library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.2.3## Warning: package 'tibble' was built under R version 4.2.3## Warning: package 'tidyr' was built under R version 4.2.3## Warning: package 'readr' was built under R version 4.2.3## Warning: package 'purrr' was built under R version 4.2.3## Warning: package 'dplyr' was built under R version 4.2.3## Warning: package 'stringr' was built under R version 4.2.3## Warning: package 'forcats' was built under R version 4.2.3## Warning: package 'lubridate' was built under R version 4.2.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsQuestion 1A-> Descriptive Analysis
# shows how many rows and columns in the data
dim(cvbase)## [1] 40000 52# shows the attributes of the data
names(cvbase)## [1] "employstatus_1" "employstatus_2" "employstatus_3"
## [4] "employstatus_4" "employstatus_5" "employstatus_6"
## [7] "employstatus_7" "employstatus_8" "employstatus_9"
## [10] "employstatus_10" "isoFriends_inPerson" "isoOthPpl_inPerson"
## [13] "isoFriends_online" "isoOthPpl_online" "lone01"
## [16] "lone02" "lone03" "happy"
## [19] "lifeSat" "MLQ" "bor01"
## [22] "bor02" "bor03" "consp01"
## [25] "consp02" "consp03" "rankOrdLife_1"
## [28] "rankOrdLife_2" "rankOrdLife_3" "rankOrdLife_4"
## [31] "rankOrdLife_5" "rankOrdLife_6" "c19perBeh01"
## [34] "c19perBeh02" "c19perBeh03" "c19RCA01"
## [37] "c19RCA02" "c19RCA03" "coronaClose_1"
## [40] "coronaClose_2" "coronaClose_3" "coronaClose_4"
## [43] "coronaClose_5" "coronaClose_6" "gender"
## [46] "age" "edu" "coded_country"
## [49] "c19ProSo01" "c19ProSo02" "c19ProSo03"
## [52] "c19ProSo04"# shows data types of each indicator
str(cvbase)## 'data.frame': 40000 obs. of 52 variables:
## $ employstatus_1 : int NA NA 1 NA NA NA NA NA NA NA ...
## $ employstatus_2 : int 1 NA NA 1 NA NA NA NA 1 NA ...
## $ employstatus_3 : int NA NA NA NA 1 NA NA NA NA 1 ...
## $ employstatus_4 : int NA NA NA NA NA NA NA NA NA NA ...
## $ employstatus_5 : int NA NA NA NA NA NA NA 1 NA NA ...
## $ employstatus_6 : int NA 1 NA NA NA NA NA NA NA NA ...
## $ employstatus_7 : int NA NA NA NA NA NA 1 NA NA NA ...
## $ employstatus_8 : int NA NA NA NA NA NA NA NA NA NA ...
## $ employstatus_9 : int NA NA NA NA NA 1 NA 1 1 NA ...
## $ employstatus_10 : int NA NA NA NA NA NA NA 1 NA NA ...
## $ isoFriends_inPerson: int 2 3 3 5 3 3 0 1 0 2 ...
## $ isoOthPpl_inPerson : int 7 1 2 1 0 0 1 1 2 3 ...
## $ isoFriends_online : int 7 7 3 0 7 7 1 2 7 1 ...
## $ isoOthPpl_online : int 4 2 0 0 0 7 0 1 7 0 ...
## $ lone01 : int 1 2 1 4 1 3 2 3 1 1 ...
## $ lone02 : int 2 4 2 4 4 4 4 4 2 1 ...
## $ lone03 : int 1 3 1 4 1 2 1 2 1 1 ...
## $ happy : int 9 8 6 6 9 6 4 7 9 6 ...
## $ lifeSat : int 6 4 5 3 6 4 2 4 6 4 ...
## $ MLQ : int 2 1 2 1 3 1 -2 2 3 2 ...
## $ bor01 : int 1 0 2 1 1 2 0 2 -3 -2 ...
## $ bor02 : int 0 0 2 1 0 3 2 1 0 -2 ...
## $ bor03 : int 2 -1 2 1 2 -1 2 1 2 3 ...
## $ consp01 : int 7 9 4 4 9 7 10 10 10 2 ...
## $ consp02 : int 7 8 4 10 10 7 10 9 10 6 ...
## $ consp03 : int 4 8 6 3 6 6 9 10 9 6 ...
## $ rankOrdLife_1 : chr "E" "E" "F" "D" ...
## $ rankOrdLife_2 : chr "D" "D" "E" "C" ...
## $ rankOrdLife_3 : chr "F" "F" "D" "E" ...
## $ rankOrdLife_4 : chr "B" "C" "C" "B" ...
## $ rankOrdLife_5 : chr "A" "A" "A" "A" ...
## $ rankOrdLife_6 : chr "C" "B" "B" "F" ...
## $ c19perBeh01 : int 2 1 3 1 2 3 3 3 3 0 ...
## $ c19perBeh02 : int 2 2 3 3 2 3 3 3 3 2 ...
## $ c19perBeh03 : int 1 2 2 2 2 3 3 3 3 2 ...
## $ c19RCA01 : int 2 2 -1 2 2 0 2 3 3 3 ...
## $ c19RCA02 : int 3 1 2 2 2 3 2 3 3 2 ...
## $ c19RCA03 : int 1 1 -1 2 2 3 -2 1 1 2 ...
## $ coronaClose_1 : int NA NA NA NA NA NA NA NA NA NA ...
## $ coronaClose_2 : int NA NA NA NA NA NA NA NA NA NA ...
## $ coronaClose_3 : int NA NA NA NA NA NA 1 NA NA NA ...
## $ coronaClose_4 : int NA NA NA NA NA NA NA NA NA NA ...
## $ coronaClose_5 : int NA NA NA 1 NA NA NA NA NA NA ...
## $ coronaClose_6 : int 1 1 1 NA 1 1 NA 1 1 1 ...
## $ gender : int 1 1 1 2 2 1 2 1 1 2 ...
## $ age : int 2 3 2 3 6 1 7 4 3 4 ...
## $ edu : int 4 6 6 4 3 5 5 4 6 4 ...
## $ coded_country : chr "Netherlands" "Kazakhstan" "Germany" "Philippines" ...
## $ c19ProSo01 : int 2 1 3 2 2 1 2 2 -2 -1 ...
## $ c19ProSo02 : int 1 1 3 1 2 0 0 2 -2 -3 ...
## $ c19ProSo03 : int 0 1 3 1 2 0 1 2 -3 -2 ...
## $ c19ProSo04 : int 2 1 3 1 2 2 3 2 -3 2 ...The data is created with the objective of analysing behaviours of each country during the pandemic in 2019 by holding multiple responses from respondents of particular countries after the survey. It holds 40,000 observations and 52 attributes that are attributable to the “Pre-Social Behaviour of 2019” analysis. Observing the attributes of the data, it holds mostly integers and characters.
Concerning the numerical attributes, the data includes employment status, loneliness, satisfaction, age, education, corona pre-social behaviors, the isolation, boredom, conspiracy, proximity.
summary(cvbase)## employstatus_1 employstatus_2 employstatus_3 employstatus_4
## Min. :1 Min. :1 Min. :1 Min. :1
## 1st Qu.:1 1st Qu.:1 1st Qu.:1 1st Qu.:1
## Median :1 Median :1 Median :1 Median :1
## Mean :1 Mean :1 Mean :1 Mean :1
## 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :34342 NA's :33216 NA's :29156 NA's :36481
## employstatus_5 employstatus_6 employstatus_7 employstatus_8
## Min. :1 Min. :1 Min. :1 Min. :1
## 1st Qu.:1 1st Qu.:1 1st Qu.:1 1st Qu.:1
## Median :1 Median :1 Median :1 Median :1
## Mean :1 Mean :1 Mean :1 Mean :1
## 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :37969 NA's :36901 NA's :36377 NA's :39250
## employstatus_9 employstatus_10 isoFriends_inPerson isoOthPpl_inPerson
## Min. :1 Min. :1 Min. :0.000 Min. :0.000
## 1st Qu.:1 1st Qu.:1 1st Qu.:0.000 1st Qu.:0.000
## Median :1 Median :1 Median :1.000 Median :1.000
## Mean :1 Mean :1 Mean :2.069 Mean :1.954
## 3rd Qu.:1 3rd Qu.:1 3rd Qu.:4.000 3rd Qu.:3.000
## Max. :1 Max. :1 Max. :7.000 Max. :7.000
## NA's :31878 NA's :39080 NA's :341 NA's :552
## isoFriends_online isoOthPpl_online lone01 lone02
## Min. :0.000 Min. :0.00 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:0.00 1st Qu.:1.000 1st Qu.:2.000
## Median :5.000 Median :2.00 Median :2.000 Median :3.000
## Mean :4.394 Mean :2.85 Mean :2.416 Mean :2.663
## 3rd Qu.:7.000 3rd Qu.:5.00 3rd Qu.:3.000 3rd Qu.:4.000
## Max. :7.000 Max. :7.00 Max. :5.000 Max. :5.000
## NA's :972 NA's :1179 NA's :85 NA's :118
## lone03 happy lifeSat MLQ
## Min. :1.000 Min. : 1.000 Min. :1.00 Min. :-3.0000
## 1st Qu.:1.000 1st Qu.: 5.000 1st Qu.:3.00 1st Qu.: 0.0000
## Median :2.000 Median : 7.000 Median :4.00 Median : 1.0000
## Mean :2.079 Mean : 6.342 Mean :4.14 Mean : 0.8531
## 3rd Qu.:3.000 3rd Qu.: 8.000 3rd Qu.:5.00 3rd Qu.: 2.0000
## Max. :5.000 Max. :10.000 Max. :6.00 Max. : 3.0000
## NA's :140 NA's :510 NA's :109 NA's :114
## bor01 bor02 bor03 consp01
## Min. :-3.0000 Min. :-3.00000 Min. :-3.0000 Min. : 0.000
## 1st Qu.:-1.0000 1st Qu.:-2.00000 1st Qu.:-1.0000 1st Qu.: 5.000
## Median : 0.0000 Median : 0.00000 Median : 0.0000 Median : 7.000
## Mean : 0.3304 Mean : 0.04674 Mean : 0.3069 Mean : 6.832
## 3rd Qu.: 2.0000 3rd Qu.: 2.00000 3rd Qu.: 2.0000 3rd Qu.: 9.000
## Max. : 3.0000 Max. : 3.00000 Max. : 3.0000 Max. :10.000
## NA's :153 NA's :164 NA's :163 NA's :1527
## consp02 consp03 rankOrdLife_1 rankOrdLife_2
## Min. : 0.000 Min. : 0.00 Length:40000 Length:40000
## 1st Qu.: 5.000 1st Qu.: 4.00 Class :character Class :character
## Median : 8.000 Median : 5.00 Mode :character Mode :character
## Mean : 7.148 Mean : 5.58
## 3rd Qu.: 9.000 3rd Qu.: 8.00
## Max. :10.000 Max. :10.00
## NA's :1556 NA's :1576
## rankOrdLife_3 rankOrdLife_4 rankOrdLife_5 rankOrdLife_6
## Length:40000 Length:40000 Length:40000 Length:40000
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## c19perBeh01 c19perBeh02 c19perBeh03 c19RCA01
## Min. :-3.000 Min. :-3.000 Min. :-3.000 Min. :-3.00
## 1st Qu.: 2.000 1st Qu.: 2.000 1st Qu.: 1.000 1st Qu.: 0.00
## Median : 3.000 Median : 3.000 Median : 2.000 Median : 2.00
## Mean : 2.311 Mean : 2.432 Mean : 1.843 Mean : 1.27
## 3rd Qu.: 3.000 3rd Qu.: 3.000 3rd Qu.: 3.000 3rd Qu.: 3.00
## Max. : 3.000 Max. : 3.000 Max. : 3.000 Max. : 3.00
## NA's :128 NA's :126 NA's :132 NA's :132
## c19RCA02 c19RCA03 coronaClose_1 coronaClose_2
## Min. :-3.000 Min. :-3.000 Min. :1 Min. :1
## 1st Qu.: 2.000 1st Qu.: 0.000 1st Qu.:1 1st Qu.:1
## Median : 3.000 Median : 2.000 Median :1 Median :1
## Mean : 2.056 Mean : 1.162 Mean :1 Mean :1
## 3rd Qu.: 3.000 3rd Qu.: 3.000 3rd Qu.:1 3rd Qu.:1
## Max. : 3.000 Max. : 3.000 Max. :1 Max. :1
## NA's :142 NA's :145 NA's :39456 NA's :38741
## coronaClose_3 coronaClose_4 coronaClose_5 coronaClose_6
## Min. :1 Min. :1 Min. :1 Min. :1
## 1st Qu.:1 1st Qu.:1 1st Qu.:1 1st Qu.:1
## Median :1 Median :1 Median :1 Median :1
## Mean :1 Mean :1 Mean :1 Mean :1
## 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1 3rd Qu.:1
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :38401 NA's :35098 NA's :35542 NA's :10718
## gender age edu coded_country
## Min. :1.000 Min. :1.000 Min. :1.000 Length:40000
## 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:4.000 Class :character
## Median :1.000 Median :3.000 Median :5.000 Mode :character
## Mean :1.391 Mean :2.901 Mean :4.406
## 3rd Qu.:2.000 3rd Qu.:4.000 3rd Qu.:5.000
## Max. :3.000 Max. :8.000 Max. :7.000
## NA's :228 NA's :250 NA's :268
## c19ProSo01 c19ProSo02 c19ProSo03 c19ProSo04
## Min. :-3.0000 Min. :-3.0000 Min. :-3.0000 Min. :-3.000
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.000
## Median : 1.0000 Median : 1.0000 Median : 1.0000 Median : 2.000
## Mean : 0.9778 Mean : 0.6817 Mean : 0.5512 Mean : 1.291
## 3rd Qu.: 2.0000 3rd Qu.: 2.0000 3rd Qu.: 2.0000 3rd Qu.: 2.000
## Max. : 3.0000 Max. : 3.0000 Max. : 3.0000 Max. : 3.000
## NA's :125 NA's :137 NA's :145 NA's :153Missing Values
# calculate the number of missing values in each column
colSums(is.na(cvbase))## employstatus_1 employstatus_2 employstatus_3 employstatus_4
## 34342 33216 29156 36481
## employstatus_5 employstatus_6 employstatus_7 employstatus_8
## 37969 36901 36377 39250
## employstatus_9 employstatus_10 isoFriends_inPerson isoOthPpl_inPerson
## 31878 39080 341 552
## isoFriends_online isoOthPpl_online lone01 lone02
## 972 1179 85 118
## lone03 happy lifeSat MLQ
## 140 510 109 114
## bor01 bor02 bor03 consp01
## 153 164 163 1527
## consp02 consp03 rankOrdLife_1 rankOrdLife_2
## 1556 1576 1706 1706
## rankOrdLife_3 rankOrdLife_4 rankOrdLife_5 rankOrdLife_6
## 1706 1706 1706 1707
## c19perBeh01 c19perBeh02 c19perBeh03 c19RCA01
## 128 126 132 132
## c19RCA02 c19RCA03 coronaClose_1 coronaClose_2
## 142 145 39456 38741
## coronaClose_3 coronaClose_4 coronaClose_5 coronaClose_6
## 38401 35098 35542 10718
## gender age edu coded_country
## 228 250 268 0
## c19ProSo01 c19ProSo02 c19ProSo03 c19ProSo04
## 125 137 145 153Distributions of Numerical Attributes.
Distributions of EmployStatus
# (1) takes all atributes related to employ status
# (2) then I use pivot_longer similar to melt
# (3) create the new columns (variable) and (frequency)
data_long_employstatus<- pivot_longer(cvbase, cols = c("employstatus_1", "employstatus_2", "employstatus_3", "employstatus_4", "employstatus_5", "employstatus_6", "employstatus_7", "employstatus_8", "employstatus_9", "employstatus_10"),
names_to = "employstatus", values_to = "value")
# Plotting
ggplot(data_long_employstatus, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~employstatus, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Employ Status",
x = "Response",
y = "Frequency")## Warning: Removed 354650 rows containing non-finite outside the scale range
## (`stat_bin()`).
Distributions of Conspiracy
data_long<- pivot_longer(cvbase, cols = c("consp01", "consp02", "consp03"),
names_to = "conspiracy", values_to = "value")
# Plotting
ggplot(data_long, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~conspiracy, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Conspiracy Beliefs",
x = "Response",
y = "Frequency")## Warning: Removed 4659 rows containing non-finite outside the scale range
## (`stat_bin()`).
Distribution of Isolation and Loneliness
data_long_isolation_and_loneliness<- pivot_longer(cvbase, cols = c("isoFriends_inPerson", "isoOthPpl_inPerson",
"isoFriends_online", "isoOthPpl_online", "lone01", "lone02", "lone03"),
names_to = "isolation_and_loneliness", values_to = "value")
# Plotting
ggplot(data_long_isolation_and_loneliness, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~isolation_and_loneliness, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Isolation and Loneliness",
x = "Response",
y = "Frequency")## Warning: Removed 3387 rows containing non-finite outside the scale range
## (`stat_bin()`).
Distribution of Happiness and Boredom
data_long_lifesat_and_boredom<- pivot_longer(cvbase, cols = c("happy", "lifeSat", "MLQ", "bor01", "bor02", "bor03"),
names_to = "life_sat_and_boredom", values_to = "value")
# Plotting
ggplot(data_long_lifesat_and_boredom, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~life_sat_and_boredom, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Life Satisfaction and Boredom",
x = "Response",
y = "Frequency")## Warning: Removed 1213 rows containing non-finite outside the scale range
## (`stat_bin()`).
Distribution of Personal Behavior and Radical Action
data_long_personalbehavior_and_radicalaction <- pivot_longer(cvbase, cols = c("c19perBeh01", "c19perBeh02", "c19perBeh03", "c19RCA01", "c19RCA02", "c19RCA03"),
names_to = "personalbehavior_and_radicalaction", values_to = "value")
# Plotting
ggplot(data_long_personalbehavior_and_radicalaction, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~personalbehavior_and_radicalaction, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Personal Behavior and Radical Action",
x = "Response",
y = "Frequency")## Warning: Removed 805 rows containing non-finite outside the scale range
## (`stat_bin()`).
Distribution of Proximity and PreSocial Behavior
data_long_proximity_and_presocial_behavior <- pivot_longer(cvbase, cols = c("coronaClose_1", "coronaClose_2", "coronaClose_3", "coronaClose_4","coronaClose_5", "coronaClose_6", "c19ProSo01", "c19ProSo02", "c19ProSo03", "c19ProSo04"),
names_to = "proximity_and_presocial_behavior", values_to = "value")
# Plotting
ggplot(data_long_proximity_and_presocial_behavior, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") + # Adjust bin size as needed
facet_wrap(~proximity_and_presocial_behavior, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Proximity and PreSocial Behavior",
x = "Response",
y = "Frequency")## Warning: Removed 198516 rows containing non-finite outside the scale range
## (`stat_bin()`).
Question 1B -> Pre-Processing / Data Manipulation
Descriptive Analysis (Happy and Social Isolation) => Graph 1
# select certain indicators for analysing happiness and social
analysis1 <- cvbase
# calculate social isolation rate for each respondent
analysis1$averageIsolation <- round(rowMeans(analysis1[,c("isoFriends_inPerson", "isoOthPpl_inPerson", "isoFriends_online", "isoOthPpl_online")], na.rm = TRUE))
# create 3 categories for average social Isolation (Low, Medium, and High)
analysis1$iso_category <- cut(analysis1$averageIsolation, breaks=3, labels=c("Low", "Medium", "High"))
# show the data without any empty rows with respect to happy and isolation category
analysis1 <- analysis1 %>%
filter(!is.na(analysis1$happy) & !is.na(analysis1$iso_category))
# convert data type of category to the factor as it has 3 main labels
analysis1$iso_category <- as.factor(analysis1$iso_category)
# plot the data
analysis1 %>%
# define the aesthetic with respect to 3 labels colored differently
ggplot(aes(x=analysis1$happy, fill=analysis1$iso_category)) +
geom_histogram(position="dodge", binwidth=1) +
labs(title="Histogram of Happiness by Social Isolation Category", x="Happiness", y="Social Isolation") +
# color the graph based on the palette
scale_fill_brewer(palette="Pastel1") +
theme_minimal()## Warning: Use of `analysis1$happy` is discouraged.
## ℹ Use `happy` instead.## Warning: Use of `analysis1$iso_category` is discouraged.
## ℹ Use `iso_category` instead.
# Calculate the number of missing values per column
missing_values <- colSums(is.na(cvbase))
# Calculate the threshold for removing columns (e.g., 50% of the rows)
threshold <- nrow(cvbase) * 0.50
# Identify columns that exceed the threshold
columns_to_remove <- names(missing_values[missing_values > threshold])
# Remove these columns from the dataframe
cvbase <- cvbase[, !(names(cvbase) %in% columns_to_remove)]Data Cleaning: Using Imputation Method
for(column_name in names(cvbase))
{
# select if the column data type is numeric
if (is.numeric(cvbase[[column_name]]))
{
cvbase[[column_name]][is.na(cvbase[[column_name]])] <- 0
cvbase[[column_name]] <- as.numeric(cvbase[[column_name]])
}
else
{
cvbase[[column_name]][is.na(cvbase[[column_name]])] <- "None"
cvbase[[column_name]] <- as.factor(cvbase[[column_name]])
}
}Convert Data Type
# change the label of gender to M, F, Others
cvbase$gender <- factor(cvbase$gender, levels = c(0, 1, 2, 3), labels = c("None", "Male", "Female", "Other"))
cvbase$edu <- factor(cvbase$edu, levels = c(0,1,2,3,4,5,6,7), labels = c("None","Primary education", "General secondary
education","Vocational education","Higher
education", "Bachelors degree", "Masters degree", "PhD
degree"))Question 2A
Extract both focus country and not focus country
cvbase_focuscountry <- "South Africa"
cvbase_focuscountry_table <- cvbase[which(cvbase$coded_country == cvbase_focuscountry),]
cvbase_nonfocuscountry_table <- cvbase[which(cvbase$coded_country != cvbase_focuscountry),]Comparison Between Focus and Non With Respect to Conspiracy
# converts the data from wide to long for focus country
data_long_focuscountry <- pivot_longer(cvbase_focuscountry_table, cols = c("consp01", "consp02", "consp03"),
names_to = "conspiracy", values_to = "value") %>%
mutate(Country = "Focus")
# converts the data from wide to long for non focus country
data_long_nonfocuscountry <- pivot_longer(cvbase_nonfocuscountry_table, cols = c("consp01", "consp02", "consp03"),
names_to = "conspiracy", values_to = "value") %>%
mutate(Country = "Non-Focus")
# Combine both datasets
combined_data <- bind_rows(data_long_focuscountry, data_long_nonfocuscountry)
# Plotting histogram with ggplot2
ggplot(combined_data, aes(x = value)) +
geom_histogram(bins = 10, fill = "blue", color = "black") +
# Adjust bin size as needed and combine all graphs with respect to the aspects required
facet_grid(Country ~ conspiracy, scales = "free") +
# create minimalistic background
theme_minimal() +
# creates the label for x and y axis, and the title
labs(title = "Distribution of Conspiracy Beliefs by Country",
x = "Response",
y = "Frequency")
# shows the comparison through the hypothesis testing
t.test(cvbase_focuscountry_table$consp01, cvbase_nonfocuscountry_table$consp01, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$consp01 and cvbase_nonfocuscountry_table$consp01
## t = 6.5944, df = 954.92, p-value = 3.528e-11
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.4293746 Inf
## sample estimates:
## mean of x mean of y
## 7.130820 6.558571t.test(cvbase_focuscountry_table$consp02, cvbase_nonfocuscountry_table$consp02, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$consp02 and cvbase_nonfocuscountry_table$consp02
## t = 7.9016, df = 958.4, p-value = 3.766e-15
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.5190294 Inf
## sample estimates:
## mean of x mean of y
## 7.511086 6.855440t.test(cvbase_focuscountry_table$consp03, cvbase_nonfocuscountry_table$consp03, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$consp03 and cvbase_nonfocuscountry_table$consp03
## t = 3.0574, df = 951.06, p-value = 0.001148
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.1252683 Inf
## sample estimates:
## mean of x mean of y
## 5.625277 5.353829Comparison Between Focus and Non Focus With Respect to Pre-Social Behaviors
data_long_focuscountry <- pivot_longer(cvbase_focuscountry_table, cols = c("c19ProSo01", "c19ProSo02", "c19ProSo03", "c19ProSo04"),
names_to = "presocialBehavior", values_to = "value") %>%
mutate(Country = "Focus")
data_long_nonfocuscountry <- pivot_longer(cvbase_nonfocuscountry_table, cols = c("c19ProSo01", "c19ProSo02", "c19ProSo03", "c19ProSo04"),
names_to = "presocialBehavior", values_to = "value") %>%
mutate(Country = "Non-Focus")
# Combine both datasets
combined_data <- bind_rows(data_long_focuscountry, data_long_nonfocuscountry)
# Plotting with ggplot2
ggplot(combined_data, aes(x = value)) +
geom_histogram(bins = 10, fill = "red", color = "black") + # Adjust bin size as needed
facet_grid(Country ~ presocialBehavior, scales = "free") +
theme_minimal() +
labs(title = "Distribution of Pre-Social Behavior by Country Category",
x = "Response",
y = "Frequency")
t.test(cvbase_focuscountry_table$c19ProSo01, cvbase_nonfocuscountry_table$c19ProSo01, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$c19ProSo01 and cvbase_nonfocuscountry_table$c19ProSo01
## t = -2.705, df = 938.71, p-value = 0.9965
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.2267019 Inf
## sample estimates:
## mean of x mean of y
## 0.8370288 0.9779528t.test(cvbase_focuscountry_table$c19ProSo02, cvbase_nonfocuscountry_table$c19ProSo02, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$c19ProSo02 and cvbase_nonfocuscountry_table$c19ProSo02
## t = -0.60632, df = 949, p-value = 0.7278
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.1170447 Inf
## sample estimates:
## mean of x mean of y
## 0.6485588 0.6800604t.test(cvbase_focuscountry_table$c19ProSo03, cvbase_nonfocuscountry_table$c19ProSo03, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$c19ProSo03 and cvbase_nonfocuscountry_table$c19ProSo03
## t = -3.4459, df = 942.08, p-value = 0.9997
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## -0.2888599 Inf
## sample estimates:
## mean of x mean of y
## 0.3580931 0.5535577t.test(cvbase_focuscountry_table$c19ProSo04, cvbase_nonfocuscountry_table$c19ProSo04, alternative = "greater")##
## Welch Two Sample t-test
##
## data: cvbase_focuscountry_table$c19ProSo04 and cvbase_nonfocuscountry_table$c19ProSo04
## t = 6.7341, df = 954.67, p-value = 1.423e-11
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.2387933 Inf
## sample estimates:
## mean of x mean of y
## 1.595344 1.279273Question 2B
Extract the table of focus country by excluding the country name
# Extracts the data by removing coded country
# this is because the "coded country" column has 1 unique value
cvbase_focuscountry_table_withoutcoded <- cvbase_focuscountry_table %>%
select(-coded_country)Identify Best Predictors for C19ProSo01
# (1) use linear regression to find independent variable used for predicting the dependable variable
fit_focuscountry_1 <- lm(cvbase_focuscountry_table_withoutcoded$c19ProSo01 ~., data = cvbase_focuscountry_table_withoutcoded)
# shows the summary of linear model
summary(fit_focuscountry_1)##
## Call:
## lm(formula = cvbase_focuscountry_table_withoutcoded$c19ProSo01 ~
## ., data = cvbase_focuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0619 -0.6701 0.1520 0.8516 3.9849
##
## Coefficients: (10 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.046e+00 1.221e+00 0.857 0.39174
## isoFriends_inPerson 1.012e-02 2.144e-02 0.472 0.63702
## isoOthPpl_inPerson 2.212e-02 2.366e-02 0.935 0.35027
## isoFriends_online 2.830e-02 2.134e-02 1.326 0.18507
## isoOthPpl_online -2.616e-02 2.060e-02 -1.269 0.20463
## lone01 1.077e-02 5.651e-02 0.190 0.84897
## lone02 -8.790e-03 5.103e-02 -0.172 0.86329
## lone03 2.588e-02 5.322e-02 0.486 0.62682
## happy 8.882e-03 2.940e-02 0.302 0.76263
## lifeSat -1.493e-02 5.202e-02 -0.287 0.77424
## MLQ 3.606e-02 4.223e-02 0.854 0.39342
## bor01 5.938e-02 3.362e-02 1.766 0.07776 .
## bor02 -3.539e-02 3.393e-02 -1.043 0.29732
## bor03 7.281e-05 2.856e-02 0.003 0.99797
## consp01 3.370e-02 2.498e-02 1.349 0.17774
## consp02 -3.767e-02 2.633e-02 -1.430 0.15299
## consp03 2.550e-02 1.884e-02 1.354 0.17607
## rankOrdLife_1B 1.875e-02 3.500e-01 0.054 0.95729
## rankOrdLife_1C 2.105e-01 3.315e-01 0.635 0.52573
## rankOrdLife_1D -1.518e-01 3.272e-01 -0.464 0.64289
## rankOrdLife_1E 3.979e-01 3.223e-01 1.234 0.21742
## rankOrdLife_1F 2.335e-01 2.969e-01 0.786 0.43182
## rankOrdLife_1None 3.220e-03 7.300e-01 0.004 0.99648
## rankOrdLife_2B -8.142e-02 2.307e-01 -0.353 0.72419
## rankOrdLife_2C -5.311e-02 2.207e-01 -0.241 0.80989
## rankOrdLife_2D -3.260e-01 2.275e-01 -1.433 0.15221
## rankOrdLife_2E 2.598e-01 2.449e-01 1.061 0.28908
## rankOrdLife_2F -6.555e-02 3.219e-01 -0.204 0.83872
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B -1.402e-01 3.334e-01 -0.420 0.67429
## rankOrdLife_3C -5.674e-02 3.258e-01 -0.174 0.86180
## rankOrdLife_3D -1.935e-01 3.291e-01 -0.588 0.55675
## rankOrdLife_3E 8.421e-02 3.201e-01 0.263 0.79256
## rankOrdLife_3F 5.309e-02 3.245e-01 0.164 0.87010
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -3.089e-02 2.205e-01 -0.140 0.88865
## rankOrdLife_4C -2.903e-02 2.149e-01 -0.135 0.89255
## rankOrdLife_4D -2.366e-01 2.457e-01 -0.963 0.33590
## rankOrdLife_4E 3.667e-01 2.715e-01 1.351 0.17720
## rankOrdLife_4F 3.147e-01 3.122e-01 1.008 0.31376
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -1.716e-01 1.653e-01 -1.038 0.29943
## rankOrdLife_5C 1.533e-02 2.050e-01 0.075 0.94039
## rankOrdLife_5D -4.537e-01 2.664e-01 -1.703 0.08897 .
## rankOrdLife_5E 3.388e-01 2.831e-01 1.197 0.23172
## rankOrdLife_5F -3.507e-01 4.127e-01 -0.850 0.39561
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B NA NA NA NA
## rankOrdLife_6C NA NA NA NA
## rankOrdLife_6D NA NA NA NA
## rankOrdLife_6E NA NA NA NA
## rankOrdLife_6F NA NA NA NA
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 9.948e-02 5.715e-02 1.740 0.08214 .
## c19perBeh02 -3.282e-02 7.621e-02 -0.431 0.66684
## c19perBeh03 -3.776e-02 4.328e-02 -0.873 0.38318
## c19RCA01 4.825e-02 2.618e-02 1.843 0.06568 .
## c19RCA02 -1.480e-02 5.078e-02 -0.291 0.77076
## c19RCA03 3.247e-02 4.077e-02 0.797 0.42597
## coronaClose_6 2.309e-02 1.397e-01 0.165 0.86876
## genderMale -1.556e+00 1.123e+00 -1.386 0.16626
## genderFemale -1.275e+00 1.123e+00 -1.135 0.25660
## genderOther -6.842e-01 1.478e+00 -0.463 0.64348
## age 4.971e-02 3.262e-02 1.524 0.12797
## eduPrimary education 3.684e-01 6.395e-01 0.576 0.56465
## eduGeneral secondary\neducation 3.810e-02 5.736e-01 0.066 0.94706
## eduVocational education 1.059e-01 5.895e-01 0.180 0.85746
## eduHigher\neducation 7.949e-02 5.704e-01 0.139 0.88919
## eduBachelors degree 2.561e-01 5.734e-01 0.447 0.65521
## eduMasters degree 2.861e-01 5.930e-01 0.482 0.62964
## eduPhD\ndegree 1.219e-01 6.789e-01 0.179 0.85759
## c19ProSo02 2.363e-01 3.709e-02 6.373 3.06e-10 ***
## c19ProSo03 2.456e-01 3.481e-02 7.056 3.58e-12 ***
## c19ProSo04 1.009e-01 3.780e-02 2.668 0.00777 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.311 on 838 degrees of freedom
## Multiple R-squared: 0.3332, Adjusted R-squared: 0.2831
## F-statistic: 6.648 on 63 and 838 DF, p-value: < 2.2e-16Identify Best Predictors for C19ProSo02
fit_focuscountry_2 <- lm(cvbase_focuscountry_table_withoutcoded$c19ProSo02 ~., data = cvbase_focuscountry_table_withoutcoded)
summary(fit_focuscountry_2)##
## Call:
## lm(formula = cvbase_focuscountry_table_withoutcoded$c19ProSo02 ~
## ., data = cvbase_focuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.2234 -0.6873 0.0769 0.7470 3.2689
##
## Coefficients: (10 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.6074058 1.1098606 -1.448 0.1479
## isoFriends_inPerson -0.0297522 0.0194789 -1.527 0.1270
## isoOthPpl_inPerson -0.0165531 0.0215303 -0.769 0.4422
## isoFriends_online -0.0086914 0.0194302 -0.447 0.6548
## isoOthPpl_online 0.0358779 0.0187208 1.916 0.0556 .
## lone01 0.0365553 0.0513935 0.711 0.4771
## lone02 -0.0088567 0.0464205 -0.191 0.8487
## lone03 0.0572754 0.0483777 1.184 0.2368
## happy 0.0270126 0.0267272 1.011 0.3125
## lifeSat -0.0072666 0.0473211 -0.154 0.8780
## MLQ 0.0902635 0.0383089 2.356 0.0187 *
## bor01 -0.0184541 0.0306376 -0.602 0.5471
## bor02 0.0413469 0.0308556 1.340 0.1806
## bor03 -0.0171348 0.0259739 -0.660 0.5096
## consp01 -0.0169678 0.0227431 -0.746 0.4558
## consp02 0.0288051 0.0239634 1.202 0.2297
## consp03 -0.0147567 0.0171454 -0.861 0.3897
## rankOrdLife_1B -0.1214995 0.3183462 -0.382 0.7028
## rankOrdLife_1C -0.0005939 0.3016558 -0.002 0.9984
## rankOrdLife_1D 0.0576784 0.2976758 0.194 0.8464
## rankOrdLife_1E -0.0079603 0.2934863 -0.027 0.9784
## rankOrdLife_1F 0.0293344 0.2701928 0.109 0.9136
## rankOrdLife_1None -0.1966368 0.6640694 -0.296 0.7672
## rankOrdLife_2B -0.1646730 0.2097591 -0.785 0.4326
## rankOrdLife_2C -0.0611873 0.2007546 -0.305 0.7606
## rankOrdLife_2D -0.3186515 0.2069121 -1.540 0.1239
## rankOrdLife_2E -0.2911793 0.2227162 -1.307 0.1914
## rankOrdLife_2F -0.3239504 0.2926531 -1.107 0.2686
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B -0.3101391 0.3031194 -1.023 0.3065
## rankOrdLife_3C -0.1554012 0.2963615 -0.524 0.6002
## rankOrdLife_3D -0.3280219 0.2991970 -1.096 0.2732
## rankOrdLife_3E -0.1973834 0.2911345 -0.678 0.4980
## rankOrdLife_3F -0.0552062 0.2952305 -0.187 0.8517
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -0.2059960 0.2004722 -1.028 0.3045
## rankOrdLife_4C -0.2199088 0.1953295 -1.126 0.2606
## rankOrdLife_4D -0.0586533 0.2236268 -0.262 0.7932
## rankOrdLife_4E -0.1961302 0.2471923 -0.793 0.4278
## rankOrdLife_4F -0.2112486 0.2840747 -0.744 0.4573
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.0323847 0.1504744 -0.215 0.8297
## rankOrdLife_5C -0.3095272 0.1861693 -1.663 0.0968 .
## rankOrdLife_5D -0.0287979 0.2427653 -0.119 0.9056
## rankOrdLife_5E -0.0866524 0.2577048 -0.336 0.7368
## rankOrdLife_5F -0.3403268 0.3753775 -0.907 0.3649
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B NA NA NA NA
## rankOrdLife_6C NA NA NA NA
## rankOrdLife_6D NA NA NA NA
## rankOrdLife_6E NA NA NA NA
## rankOrdLife_6F NA NA NA NA
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 0.0697138 0.0520307 1.340 0.1807
## c19perBeh02 0.0785671 0.0692792 1.134 0.2571
## c19perBeh03 0.0126616 0.0393822 0.322 0.7479
## c19RCA01 0.0442361 0.0238126 1.858 0.0636 .
## c19RCA02 0.0017669 0.0461954 0.038 0.9695
## c19RCA03 -0.0160636 0.0370984 -0.433 0.6651
## coronaClose_6 -0.2642784 0.1267523 -2.085 0.0374 *
## genderMale 1.0372399 1.0218921 1.015 0.3104
## genderFemale 0.9085923 1.0221643 0.889 0.3743
## genderOther 0.8289580 1.3441395 0.617 0.5376
## age -0.0281117 0.0297031 -0.946 0.3442
## eduPrimary education 0.8340799 0.5811009 1.435 0.1516
## eduGeneral secondary\neducation 0.9840391 0.5207104 1.890 0.0591 .
## eduVocational education 0.9196756 0.5353661 1.718 0.0862 .
## eduHigher\neducation 1.0142032 0.5176649 1.959 0.0504 .
## eduBachelors degree 1.1835763 0.5200724 2.276 0.0231 *
## eduMasters degree 1.0187981 0.5383753 1.892 0.0588 .
## eduPhD\ndegree 0.9595523 0.6167222 1.556 0.1201
## c19ProSo01 0.1955758 0.0306894 6.373 3.06e-10 ***
## c19ProSo03 0.3854068 0.0297507 12.955 < 2e-16 ***
## c19ProSo04 0.0162152 0.0345316 0.470 0.6388
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.193 on 838 degrees of freedom
## Multiple R-squared: 0.4422, Adjusted R-squared: 0.4003
## F-statistic: 10.54 on 63 and 838 DF, p-value: < 2.2e-16Identify Best Predictors for C19ProSo03
fit_focuscountry_3 <- lm(cvbase_focuscountry_table_withoutcoded$c19ProSo03 ~., data = cvbase_focuscountry_table_withoutcoded)
summary(fit_focuscountry_3)##
## Call:
## lm(formula = cvbase_focuscountry_table_withoutcoded$c19ProSo03 ~
## ., data = cvbase_focuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9559 -0.6438 0.1607 0.7436 3.7476
##
## Coefficients: (10 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.611114 1.177562 -0.519 0.60392
## isoFriends_inPerson 0.003147 0.020673 0.152 0.87905
## isoOthPpl_inPerson 0.001368 0.022827 0.060 0.95223
## isoFriends_online 0.013012 0.020591 0.632 0.52761
## isoOthPpl_online 0.003240 0.019884 0.163 0.87059
## lone01 0.082383 0.054411 1.514 0.13038
## lone02 -0.068813 0.049142 -1.400 0.16180
## lone03 0.029435 0.051306 0.574 0.56631
## happy -0.017989 0.028337 -0.635 0.52572
## lifeSat 0.052289 0.050121 1.043 0.29713
## MLQ 0.047632 0.040703 1.170 0.24223
## bor01 0.048571 0.032435 1.497 0.13464
## bor02 -0.030288 0.032720 -0.926 0.35489
## bor03 0.059713 0.027458 2.175 0.02993 *
## consp01 -0.025600 0.024096 -1.062 0.28836
## consp02 -0.025919 0.025404 -1.020 0.30789
## consp03 0.017396 0.018170 0.957 0.33862
## rankOrdLife_1B 0.439945 0.337084 1.305 0.19220
## rankOrdLife_1C 0.270514 0.319572 0.846 0.39752
## rankOrdLife_1D 0.340524 0.315278 1.080 0.28042
## rankOrdLife_1E 0.445036 0.310670 1.433 0.15237
## rankOrdLife_1F 0.363821 0.286088 1.272 0.20383
## rankOrdLife_1None 0.746224 0.703375 1.061 0.28903
## rankOrdLife_2B 0.120052 0.222355 0.540 0.58940
## rankOrdLife_2C 0.133088 0.212731 0.626 0.53174
## rankOrdLife_2D 0.289357 0.219377 1.319 0.18753
## rankOrdLife_2E 0.294757 0.236066 1.249 0.21215
## rankOrdLife_2F 0.376733 0.310121 1.215 0.22479
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 0.017475 0.321460 0.054 0.95666
## rankOrdLife_3C 0.150339 0.314106 0.479 0.63233
## rankOrdLife_3D 0.025131 0.317329 0.079 0.93690
## rankOrdLife_3E -0.063918 0.308634 -0.207 0.83598
## rankOrdLife_3F -0.003896 0.312905 -0.012 0.99007
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B 0.300637 0.212349 1.416 0.15722
## rankOrdLife_4C 0.337741 0.206847 1.633 0.10289
## rankOrdLife_4D 0.376743 0.236662 1.592 0.11178
## rankOrdLife_4E 0.057889 0.262076 0.221 0.82523
## rankOrdLife_4F 0.607862 0.300441 2.023 0.04337 *
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B 0.218173 0.159306 1.370 0.17120
## rankOrdLife_5C 0.033868 0.197632 0.171 0.86398
## rankOrdLife_5D 0.170627 0.257228 0.663 0.50730
## rankOrdLife_5E 0.320867 0.272921 1.176 0.24006
## rankOrdLife_5F 0.575698 0.397540 1.448 0.14795
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B NA NA NA NA
## rankOrdLife_6C NA NA NA NA
## rankOrdLife_6D NA NA NA NA
## rankOrdLife_6E NA NA NA NA
## rankOrdLife_6F NA NA NA NA
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 -0.063646 0.055160 -1.154 0.24889
## c19perBeh02 0.042062 0.073467 0.573 0.56712
## c19perBeh03 0.034941 0.041724 0.837 0.40259
## c19RCA01 -0.024753 0.025275 -0.979 0.32769
## c19RCA02 -0.004642 0.048960 -0.095 0.92448
## c19RCA03 -0.013569 0.039320 -0.345 0.73012
## coronaClose_6 0.117716 0.134624 0.874 0.38215
## genderMale 0.104045 1.083706 0.096 0.92354
## genderFemale 0.253120 1.083811 0.234 0.81539
## genderOther 0.704757 1.424694 0.495 0.62096
## age -0.083504 0.031365 -2.662 0.00791 **
## eduPrimary education -0.559758 0.616330 -0.908 0.36403
## eduGeneral secondary\neducation -0.983222 0.552003 -1.781 0.07524 .
## eduVocational education -0.598513 0.568027 -1.054 0.29234
## eduHigher\neducation -0.819672 0.549170 -1.493 0.13593
## eduBachelors degree -0.937410 0.551948 -1.698 0.08981 .
## eduMasters degree -0.944950 0.570880 -1.655 0.09825 .
## eduPhD\ndegree -0.672021 0.654161 -1.027 0.30458
## c19ProSo01 0.228325 0.032357 7.056 3.58e-12 ***
## c19ProSo02 0.432916 0.033418 12.955 < 2e-16 ***
## c19ProSo04 0.268388 0.035409 7.580 9.19e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.264 on 838 degrees of freedom
## Multiple R-squared: 0.4763, Adjusted R-squared: 0.4369
## F-statistic: 12.1 on 63 and 838 DF, p-value: < 2.2e-16Identify Best Predictors for C19ProSo04
fit_focuscountry_4 <- lm(cvbase_focuscountry_table_withoutcoded$c19ProSo04 ~., data = cvbase_focuscountry_table_withoutcoded)
summary(fit_focuscountry_4)##
## Call:
## lm(formula = cvbase_focuscountry_table_withoutcoded$c19ProSo04 ~
## ., data = cvbase_focuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.4525 -0.5696 0.1106 0.7817 2.7698
##
## Coefficients: (10 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.1025644 1.1115107 -0.092 0.926502
## isoFriends_inPerson 0.0194318 0.0194991 0.997 0.319273
## isoOthPpl_inPerson 0.0275265 0.0215221 1.279 0.201255
## isoFriends_online 0.0236066 0.0194201 1.216 0.224489
## isoOthPpl_online 0.0002417 0.0187663 0.013 0.989728
## lone01 0.0418845 0.0514010 0.815 0.415385
## lone02 0.0263978 0.0464237 0.569 0.569761
## lone03 -0.0360179 0.0484138 -0.744 0.457110
## happy 0.0108907 0.0267473 0.407 0.683986
## lifeSat -0.0132121 0.0473309 -0.279 0.780204
## MLQ -0.0247750 0.0384354 -0.645 0.519370
## bor01 0.0635265 0.0305730 2.078 0.038026 *
## bor02 -0.0430032 0.0308604 -1.393 0.163845
## bor03 0.0494572 0.0259307 1.907 0.056825 .
## consp01 -0.0036032 0.0227558 -0.158 0.874226
## consp02 0.0571461 0.0239085 2.390 0.017059 *
## consp03 -0.0232523 0.0171383 -1.357 0.175228
## rankOrdLife_1B -0.6446533 0.3176709 -2.029 0.042742 *
## rankOrdLife_1C -0.2361967 0.3016181 -0.783 0.433790
## rankOrdLife_1D -0.2791363 0.2975979 -0.938 0.348533
## rankOrdLife_1E -0.0163697 0.2935565 -0.056 0.955544
## rankOrdLife_1F -0.1086930 0.2702336 -0.402 0.687626
## rankOrdLife_1None -1.0566618 0.6632604 -1.593 0.111507
## rankOrdLife_2B -0.3281692 0.2095803 -1.566 0.117764
## rankOrdLife_2C -0.1423256 0.2007539 -0.709 0.478549
## rankOrdLife_2D -0.2892804 0.2070135 -1.397 0.162663
## rankOrdLife_2E -0.3234561 0.2227168 -1.452 0.146787
## rankOrdLife_2F -0.1999578 0.2928560 -0.683 0.494931
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 0.0741011 0.3033709 0.244 0.807090
## rankOrdLife_3C 0.0544788 0.2964755 0.184 0.854250
## rankOrdLife_3D -0.0495306 0.2994787 -0.165 0.868677
## rankOrdLife_3E 0.0945313 0.2912661 0.325 0.745600
## rankOrdLife_3F 0.0066581 0.2953077 0.023 0.982018
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -0.2619890 0.2004425 -1.307 0.191553
## rankOrdLife_4C -0.0392434 0.1955196 -0.201 0.840972
## rankOrdLife_4D -0.3351080 0.2233901 -1.500 0.133964
## rankOrdLife_4E -0.0502208 0.2473386 -0.203 0.839149
## rankOrdLife_4F -0.5020063 0.2837073 -1.769 0.077182 .
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.2493636 0.1502681 -1.659 0.097398 .
## rankOrdLife_5C -0.2728097 0.1862828 -1.464 0.143435
## rankOrdLife_5D -0.5298619 0.2421349 -2.188 0.028924 *
## rankOrdLife_5E -0.3219576 0.2575442 -1.250 0.211610
## rankOrdLife_5F -0.5378359 0.3751922 -1.433 0.152090
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B NA NA NA NA
## rankOrdLife_6C NA NA NA NA
## rankOrdLife_6D NA NA NA NA
## rankOrdLife_6E NA NA NA NA
## rankOrdLife_6F NA NA NA NA
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 0.0060951 0.0520985 0.117 0.906894
## c19perBeh02 0.2469739 0.0688222 3.589 0.000352 ***
## c19perBeh03 0.0084765 0.0393930 0.215 0.829680
## c19RCA01 0.0160730 0.0238609 0.674 0.500743
## c19RCA02 0.0588852 0.0461617 1.276 0.202440
## c19RCA03 0.0631447 0.0370473 1.704 0.088671 .
## coronaClose_6 -0.0742414 0.1270853 -0.584 0.559253
## genderMale 0.2190709 1.0227382 0.214 0.830443
## genderFemale 0.0865160 1.0228879 0.085 0.932615
## genderOther -0.1994145 1.3447506 -0.148 0.882149
## age -0.0005174 0.0297262 -0.017 0.986117
## eduPrimary education 0.0608788 0.5819510 0.105 0.916709
## eduGeneral secondary\neducation 0.6840066 0.5214093 1.312 0.189933
## eduVocational education 0.6932981 0.5359021 1.294 0.196125
## eduHigher\neducation 0.5694880 0.5186010 1.098 0.272466
## eduBachelors degree 0.5339813 0.5214765 1.024 0.306140
## eduMasters degree 0.7583947 0.5390180 1.407 0.159800
## eduPhD\ndegree 1.1304745 0.6165255 1.834 0.067065 .
## c19ProSo01 0.0835145 0.0312992 2.668 0.007772 **
## c19ProSo02 0.0162230 0.0345482 0.470 0.638779
## c19ProSo03 0.2390491 0.0315385 7.580 9.19e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.193 on 838 degrees of freedom
## Multiple R-squared: 0.3141, Adjusted R-squared: 0.2626
## F-statistic: 6.092 on 63 and 838 DF, p-value: < 2.2e-16Question 2C
cvbase_nonfocuscountry_table_withoutcoded <- cvbase_nonfocuscountry_table %>%
select(-coded_country)Identify Best Predictors with C19ProSo01
fit_nonfocuscountry_1 <- lm(cvbase_nonfocuscountry_table_withoutcoded$c19ProSo01 ~., data = cvbase_nonfocuscountry_table_withoutcoded)
summary(fit_nonfocuscountry_1)##
## Call:
## lm(formula = cvbase_nonfocuscountry_table_withoutcoded$c19ProSo01 ~
## ., data = cvbase_nonfocuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.6730 -0.5962 0.1314 0.7140 4.7413
##
## Coefficients: (4 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.645124 0.289447 2.229 0.025832 *
## isoFriends_inPerson 0.006985 0.002757 2.534 0.011291 *
## isoOthPpl_inPerson 0.017111 0.003078 5.560 2.72e-08 ***
## isoFriends_online 0.007487 0.002753 2.719 0.006547 **
## isoOthPpl_online 0.006195 0.002572 2.409 0.016013 *
## lone01 0.048534 0.007528 6.447 1.16e-10 ***
## lone02 -0.022285 0.006651 -3.351 0.000807 ***
## lone03 -0.008733 0.007197 -1.213 0.225010
## happy 0.002406 0.003835 0.627 0.530389
## lifeSat -0.002315 0.007024 -0.330 0.741685
## MLQ 0.042600 0.004912 8.672 < 2e-16 ***
## bor01 0.011378 0.004220 2.696 0.007010 **
## bor02 -0.006129 0.004218 -1.453 0.146217
## bor03 0.020943 0.003978 5.265 1.41e-07 ***
## consp01 0.014086 0.003137 4.490 7.14e-06 ***
## consp02 -0.003585 0.003236 -1.108 0.268042
## consp03 0.006293 0.002488 2.529 0.011446 *
## rankOrdLife_1B -0.021543 0.089437 -0.241 0.809651
## rankOrdLife_1C -0.064321 0.098258 -0.655 0.512721
## rankOrdLife_1D -0.096948 0.103414 -0.937 0.348517
## rankOrdLife_1E -0.098553 0.095266 -1.035 0.300909
## rankOrdLife_1F -0.010314 0.081966 -0.126 0.899864
## rankOrdLife_1None -1.265399 1.204420 -1.051 0.293435
## rankOrdLife_2B 0.019021 0.086309 0.220 0.825577
## rankOrdLife_2C -0.062261 0.096221 -0.647 0.517595
## rankOrdLife_2D -0.104185 0.101580 -1.026 0.305065
## rankOrdLife_2E -0.101941 0.093517 -1.090 0.275682
## rankOrdLife_2F -0.035596 0.083120 -0.428 0.668473
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 0.057148 0.093327 0.612 0.540320
## rankOrdLife_3C -0.001464 0.101159 -0.014 0.988454
## rankOrdLife_3D -0.064292 0.106025 -0.606 0.544267
## rankOrdLife_3E -0.042172 0.097869 -0.431 0.666542
## rankOrdLife_3F 0.008884 0.085935 0.103 0.917660
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B 0.007552 0.084080 0.090 0.928436
## rankOrdLife_4C -0.105659 0.094981 -1.112 0.265962
## rankOrdLife_4D -0.137511 0.101157 -1.359 0.174033
## rankOrdLife_4E -0.165817 0.093585 -1.772 0.076429 .
## rankOrdLife_4F -0.159787 0.082596 -1.935 0.053053 .
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B 0.024591 0.083857 0.293 0.769333
## rankOrdLife_5C -0.067838 0.095228 -0.712 0.476232
## rankOrdLife_5D -0.118481 0.101908 -1.163 0.244987
## rankOrdLife_5E -0.119983 0.093802 -1.279 0.200866
## rankOrdLife_5F -0.016093 0.081513 -0.197 0.843490
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -0.064110 0.084339 -0.760 0.447171
## rankOrdLife_6C -0.195694 0.095034 -2.059 0.039482 *
## rankOrdLife_6D -0.234147 0.101031 -2.318 0.020478 *
## rankOrdLife_6E -0.276897 0.092993 -2.978 0.002907 **
## rankOrdLife_6F -0.235827 0.078785 -2.993 0.002761 **
## rankOrdLife_6None 0.740593 1.181110 0.627 0.530642
## c19perBeh01 0.087703 0.007091 12.368 < 2e-16 ***
## c19perBeh02 0.024245 0.008576 2.827 0.004698 **
## c19perBeh03 -0.030052 0.005077 -5.919 3.26e-09 ***
## c19RCA01 0.021756 0.003870 5.622 1.91e-08 ***
## c19RCA02 -0.000680 0.006141 -0.111 0.911826
## c19RCA03 -0.014971 0.004187 -3.576 0.000349 ***
## coronaClose_6 -0.058603 0.013706 -4.276 1.91e-05 ***
## genderMale -0.175069 0.098967 -1.769 0.076908 .
## genderFemale -0.091733 0.099260 -0.924 0.355403
## genderOther -0.085261 0.129826 -0.657 0.511357
## age 0.001819 0.004056 0.448 0.653923
## eduPrimary education -0.129860 0.104312 -1.245 0.213167
## eduGeneral secondary\neducation -0.105196 0.093370 -1.127 0.259893
## eduVocational education 0.016575 0.093932 0.176 0.859933
## eduHigher\neducation -0.057863 0.092590 -0.625 0.532015
## eduBachelors degree -0.040156 0.092489 -0.434 0.664167
## eduMasters degree -0.056860 0.092966 -0.612 0.540791
## eduPhD\ndegree -0.058818 0.095368 -0.617 0.537405
## c19ProSo02 0.210162 0.004514 46.561 < 2e-16 ***
## c19ProSo03 0.267839 0.004619 57.983 < 2e-16 ***
## c19ProSo04 0.116062 0.004621 25.117 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.178 on 39028 degrees of freedom
## Multiple R-squared: 0.3571, Adjusted R-squared: 0.356
## F-statistic: 314.2 on 69 and 39028 DF, p-value: < 2.2e-16Identify best predictors for C19ProSo02
fit_nonfocuscountry_2 <- lm(cvbase_nonfocuscountry_table_withoutcoded$c19ProSo02 ~., data = cvbase_nonfocuscountry_table_withoutcoded)
summary(fit_nonfocuscountry_2)##
## Call:
## lm(formula = cvbase_nonfocuscountry_table_withoutcoded$c19ProSo02 ~
## ., data = cvbase_nonfocuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.7513 -0.6851 0.1511 0.8005 5.5362
##
## Coefficients: (4 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.068298 0.315965 -0.216 0.828866
## isoFriends_inPerson 0.024920 0.003007 8.288 < 2e-16 ***
## isoOthPpl_inPerson -0.017437 0.003360 -5.190 2.11e-07 ***
## isoFriends_online 0.010273 0.003005 3.418 0.000630 ***
## isoOthPpl_online 0.010260 0.002807 3.655 0.000258 ***
## lone01 0.041178 0.008219 5.010 5.47e-07 ***
## lone02 -0.036832 0.007258 -5.075 3.90e-07 ***
## lone03 0.001734 0.007856 0.221 0.825337
## happy 0.020527 0.004185 4.905 9.38e-07 ***
## lifeSat 0.053740 0.007662 7.014 2.36e-12 ***
## MLQ 0.065734 0.005357 12.271 < 2e-16 ***
## bor01 0.051734 0.004599 11.249 < 2e-16 ***
## bor02 -0.011348 0.004604 -2.465 0.013705 *
## bor03 0.006906 0.004343 1.590 0.111845
## consp01 -0.022291 0.003423 -6.512 7.52e-11 ***
## consp02 -0.015937 0.003532 -4.512 6.43e-06 ***
## consp03 0.004199 0.002716 1.546 0.122187
## rankOrdLife_1B -0.160863 0.097621 -1.648 0.099395 .
## rankOrdLife_1C -0.109127 0.107252 -1.017 0.308932
## rankOrdLife_1D 0.203093 0.112877 1.799 0.071989 .
## rankOrdLife_1E -0.174742 0.103985 -1.680 0.092878 .
## rankOrdLife_1F -0.417319 0.089445 -4.666 3.09e-06 ***
## rankOrdLife_1None -0.588075 1.314696 -0.447 0.654655
## rankOrdLife_2B -0.130175 0.094208 -1.382 0.167047
## rankOrdLife_2C -0.042803 0.105030 -0.408 0.683620
## rankOrdLife_2D 0.305362 0.110870 2.754 0.005886 **
## rankOrdLife_2E 0.025731 0.102079 0.252 0.800989
## rankOrdLife_2F -0.251356 0.090721 -2.771 0.005597 **
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B -0.127677 0.101870 -1.253 0.210090
## rankOrdLife_3C 0.003158 0.110420 0.029 0.977183
## rankOrdLife_3D 0.285156 0.115723 2.464 0.013739 *
## rankOrdLife_3E -0.086633 0.106828 -0.811 0.417397
## rankOrdLife_3F -0.369932 0.093784 -3.945 8.01e-05 ***
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -0.107252 0.091776 -1.169 0.242560
## rankOrdLife_4C 0.038144 0.103677 0.368 0.712943
## rankOrdLife_4D 0.320275 0.110408 2.901 0.003724 **
## rankOrdLife_4E -0.017472 0.102156 -0.171 0.864203
## rankOrdLife_4F -0.286827 0.090150 -3.182 0.001466 **
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.112255 0.091532 -1.226 0.220056
## rankOrdLife_5C 0.001516 0.103946 0.015 0.988366
## rankOrdLife_5D 0.274524 0.111231 2.468 0.013589 *
## rankOrdLife_5E -0.005402 0.102392 -0.053 0.957924
## rankOrdLife_5F -0.356885 0.088957 -4.012 6.04e-05 ***
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -0.096451 0.092060 -1.048 0.294782
## rankOrdLife_6C -0.010741 0.103740 -0.104 0.917536
## rankOrdLife_6D 0.241419 0.110281 2.189 0.028593 *
## rankOrdLife_6E -0.078937 0.101517 -0.778 0.436827
## rankOrdLife_6F -0.424903 0.085980 -4.942 7.77e-07 ***
## rankOrdLife_6None 0.344102 1.289243 0.267 0.789546
## c19perBeh01 0.032301 0.007754 4.166 3.11e-05 ***
## c19perBeh02 0.024048 0.009361 2.569 0.010205 *
## c19perBeh03 0.025137 0.005543 4.535 5.77e-06 ***
## c19RCA01 0.066576 0.004213 15.804 < 2e-16 ***
## c19RCA02 -0.009369 0.006703 -1.398 0.162214
## c19RCA03 0.076272 0.004554 16.748 < 2e-16 ***
## coronaClose_6 -0.062795 0.014961 -4.197 2.71e-05 ***
## genderMale 0.235022 0.108025 2.176 0.029589 *
## genderFemale 0.156854 0.108345 1.448 0.147702
## genderOther 0.025107 0.141711 0.177 0.859376
## age -0.014712 0.004427 -3.323 0.000891 ***
## eduPrimary education -0.209731 0.113859 -1.842 0.065479 .
## eduGeneral secondary\neducation -0.202755 0.101914 -1.989 0.046657 *
## eduVocational education -0.308952 0.102519 -3.014 0.002583 **
## eduHigher\neducation -0.195247 0.101063 -1.932 0.053374 .
## eduBachelors degree -0.103313 0.100955 -1.023 0.306148
## eduMasters degree -0.065697 0.101477 -0.647 0.517370
## eduPhD\ndegree -0.022457 0.104099 -0.216 0.829198
## c19ProSo01 0.250403 0.005378 46.561 < 2e-16 ***
## c19ProSo03 0.329910 0.004982 66.214 < 2e-16 ***
## c19ProSo04 0.029158 0.005082 5.737 9.71e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.286 on 39028 degrees of freedom
## Multiple R-squared: 0.3899, Adjusted R-squared: 0.3888
## F-statistic: 361.5 on 69 and 39028 DF, p-value: < 2.2e-16Identify Best Predictors for C19ProSo03
fit_nonfocuscountry_3 <- lm(cvbase_nonfocuscountry_table_withoutcoded$c19ProSo03 ~., data = cvbase_nonfocuscountry_table_withoutcoded)
summary(fit_nonfocuscountry_3)##
## Call:
## lm(formula = cvbase_nonfocuscountry_table_withoutcoded$c19ProSo03 ~
## ., data = cvbase_nonfocuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.4295 -0.6942 0.1654 0.7319 5.7602
##
## Coefficients: (4 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -5.407e-01 3.043e-01 -1.777 0.075635 .
## isoFriends_inPerson 5.154e-03 2.899e-03 1.778 0.075372 .
## isoOthPpl_inPerson 1.551e-02 3.236e-03 4.792 1.66e-06 ***
## isoFriends_online -7.422e-03 2.895e-03 -2.564 0.010357 *
## isoOthPpl_online 1.511e-02 2.703e-03 5.590 2.29e-08 ***
## lone01 -1.684e-02 7.920e-03 -2.127 0.033447 *
## lone02 -5.926e-03 6.994e-03 -0.847 0.396856
## lone03 4.794e-02 7.564e-03 6.338 2.35e-10 ***
## happy 2.327e-03 4.032e-03 0.577 0.563829
## lifeSat 2.480e-02 7.384e-03 3.358 0.000786 ***
## MLQ -1.036e-02 5.170e-03 -2.003 0.045134 *
## bor01 -1.808e-03 4.437e-03 -0.408 0.683587
## bor02 1.347e-02 4.435e-03 3.037 0.002392 **
## bor03 1.397e-02 4.183e-03 3.340 0.000839 ***
## consp01 -1.265e-02 3.299e-03 -3.836 0.000125 ***
## consp02 -2.282e-02 3.401e-03 -6.711 1.96e-11 ***
## consp03 6.327e-03 2.617e-03 2.418 0.015603 *
## rankOrdLife_1B -1.489e-03 9.404e-02 -0.016 0.987370
## rankOrdLife_1C 1.621e-01 1.033e-01 1.569 0.116575
## rankOrdLife_1D -6.535e-02 1.087e-01 -0.601 0.547875
## rankOrdLife_1E 4.974e-02 1.002e-01 0.497 0.619487
## rankOrdLife_1F 2.046e-01 8.618e-02 2.374 0.017590 *
## rankOrdLife_1None 4.967e-01 1.266e+00 0.392 0.694912
## rankOrdLife_2B 6.638e-02 9.075e-02 0.731 0.464496
## rankOrdLife_2C 2.846e-01 1.012e-01 2.813 0.004906 **
## rankOrdLife_2D 5.082e-02 1.068e-01 0.476 0.634195
## rankOrdLife_2E 1.680e-01 9.833e-02 1.709 0.087549 .
## rankOrdLife_2F 3.241e-01 8.738e-02 3.709 0.000208 ***
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 2.439e-02 9.813e-02 0.249 0.803693
## rankOrdLife_3C 1.587e-01 1.064e-01 1.492 0.135792
## rankOrdLife_3D -4.323e-02 1.115e-01 -0.388 0.698188
## rankOrdLife_3E 4.389e-02 1.029e-01 0.427 0.669725
## rankOrdLife_3F 2.180e-01 9.035e-02 2.412 0.015851 *
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -1.650e-02 8.841e-02 -0.187 0.851920
## rankOrdLife_4C 1.745e-01 9.987e-02 1.748 0.080512 .
## rankOrdLife_4D -1.031e-01 1.064e-01 -0.969 0.332488
## rankOrdLife_4E 8.441e-03 9.840e-02 0.086 0.931642
## rankOrdLife_4F 1.750e-01 8.685e-02 2.015 0.043940 *
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B 1.431e-02 8.817e-02 0.162 0.871051
## rankOrdLife_5C 2.284e-01 1.001e-01 2.281 0.022530 *
## rankOrdLife_5D 9.828e-03 1.072e-01 0.092 0.926924
## rankOrdLife_5E 1.291e-01 9.863e-02 1.309 0.190696
## rankOrdLife_5F 2.761e-01 8.570e-02 3.221 0.001277 **
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -1.988e-03 8.868e-02 -0.022 0.982115
## rankOrdLife_6C 1.345e-01 9.993e-02 1.346 0.178273
## rankOrdLife_6D -1.241e-01 1.062e-01 -1.168 0.242911
## rankOrdLife_6E -5.609e-02 9.779e-02 -0.574 0.566259
## rankOrdLife_6F 1.746e-01 8.284e-02 2.108 0.035023 *
## rankOrdLife_6None -1.708e-02 1.242e+00 -0.014 0.989028
## c19perBeh01 -3.000e-03 7.470e-03 -0.402 0.687962
## c19perBeh02 -4.955e-03 9.018e-03 -0.549 0.582688
## c19perBeh03 1.114e-02 5.340e-03 2.086 0.036987 *
## c19RCA01 1.021e-03 4.071e-03 0.251 0.801878
## c19RCA02 -2.244e-02 6.456e-03 -3.476 0.000509 ***
## c19RCA03 -2.066e-02 4.401e-03 -4.694 2.69e-06 ***
## coronaClose_6 -1.926e-02 1.441e-02 -1.336 0.181441
## genderMale 3.171e-05 1.041e-01 0.000 0.999757
## genderFemale 2.374e-02 1.044e-01 0.227 0.820060
## genderOther 7.979e-02 1.365e-01 0.585 0.558863
## age -7.131e-02 4.250e-03 -16.781 < 2e-16 ***
## eduPrimary education 2.678e-02 1.097e-01 0.244 0.807119
## eduGeneral secondary\neducation 1.547e-02 9.818e-02 0.158 0.874785
## eduVocational education 1.193e-02 9.877e-02 0.121 0.903843
## eduHigher\neducation 1.135e-02 9.736e-02 0.117 0.907155
## eduBachelors degree 5.064e-02 9.725e-02 0.521 0.602581
## eduMasters degree 7.093e-02 9.775e-02 0.726 0.468077
## eduPhD\ndegree 1.815e-01 1.003e-01 1.810 0.070246 .
## c19ProSo01 2.961e-01 5.107e-03 57.983 < 2e-16 ***
## c19ProSo02 3.061e-01 4.623e-03 66.214 < 2e-16 ***
## c19ProSo04 3.044e-01 4.649e-03 65.483 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.238 on 39028 degrees of freedom
## Multiple R-squared: 0.4482, Adjusted R-squared: 0.4472
## F-statistic: 459.4 on 69 and 39028 DF, p-value: < 2.2e-16Identify Best Predictors for C19ProSo04
fit_nonfocuscountry_4 <- lm(cvbase_nonfocuscountry_table_withoutcoded$c19ProSo04 ~., data = cvbase_nonfocuscountry_table_withoutcoded)
summary(fit_nonfocuscountry_4)##
## Call:
## lm(formula = cvbase_nonfocuscountry_table_withoutcoded$c19ProSo04 ~
## ., data = cvbase_nonfocuscountry_table_withoutcoded)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.6953 -0.6741 0.1325 0.8001 5.6338
##
## Coefficients: (4 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.3531033 0.3145511 -1.123 0.261630
## isoFriends_inPerson -0.0164368 0.0029947 -5.489 4.08e-08 ***
## isoOthPpl_inPerson -0.0009225 0.0033458 -0.276 0.782776
## isoFriends_online 0.0116004 0.0029916 3.878 0.000106 ***
## isoOthPpl_online -0.0030730 0.0027950 -1.099 0.271579
## lone01 -0.0362782 0.0081834 -4.433 9.31e-06 ***
## lone02 0.0506738 0.0072236 7.015 2.34e-12 ***
## lone03 0.0122201 0.0078212 1.562 0.118192
## happy -0.0119964 0.0041671 -2.879 0.003994 **
## lifeSat 0.0392686 0.0076302 5.146 2.67e-07 ***
## MLQ -0.0179764 0.0053423 -3.365 0.000766 ***
## bor01 -0.0155168 0.0045850 -3.384 0.000714 ***
## bor02 0.0207246 0.0045824 4.523 6.12e-06 ***
## bor03 0.0235660 0.0043225 5.452 5.01e-08 ***
## consp01 0.0310994 0.0034062 9.130 < 2e-16 ***
## consp02 0.0038135 0.0035170 1.084 0.278235
## consp03 -0.0032435 0.0027043 -1.199 0.230393
## rankOrdLife_1B -0.0136249 0.0971890 -0.140 0.888511
## rankOrdLife_1C 0.0443169 0.1067755 0.415 0.678109
## rankOrdLife_1D 0.0101439 0.1123789 0.090 0.928077
## rankOrdLife_1E 0.3359468 0.1035114 3.246 0.001173 **
## rankOrdLife_1F 0.2268047 0.0890634 2.547 0.010883 *
## rankOrdLife_1None 1.0712549 1.3088275 0.818 0.413086
## rankOrdLife_2B 0.0445959 0.0937904 0.475 0.634444
## rankOrdLife_2C 0.0542378 0.1045618 0.519 0.603962
## rankOrdLife_2D 0.0240368 0.1103863 0.218 0.827624
## rankOrdLife_2E 0.2082895 0.1016190 2.050 0.040399 *
## rankOrdLife_2F 0.1642959 0.0903212 1.819 0.068916 .
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B -0.0260386 0.1014175 -0.257 0.797376
## rankOrdLife_3C 0.0930447 0.1099266 0.846 0.397320
## rankOrdLife_3D -0.0399203 0.1152160 -0.346 0.728982
## rankOrdLife_3E 0.2606439 0.1063446 2.451 0.014253 *
## rankOrdLife_3F 0.1945753 0.0933789 2.084 0.037192 *
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B 0.0304354 0.0913683 0.333 0.739055
## rankOrdLife_4C 0.0344162 0.1032153 0.333 0.738803
## rankOrdLife_4D -0.1031247 0.1099265 -0.938 0.348187
## rankOrdLife_4E 0.1260181 0.1016990 1.239 0.215305
## rankOrdLife_4F 0.0059417 0.0897602 0.066 0.947223
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.0224134 0.0911256 -0.246 0.805714
## rankOrdLife_5C -0.0403799 0.1034826 -0.390 0.696384
## rankOrdLife_5D -0.1395902 0.1107414 -1.261 0.207495
## rankOrdLife_5E 0.1113017 0.1019337 1.092 0.274883
## rankOrdLife_5F -0.0238572 0.0885790 -0.269 0.787675
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -0.0157834 0.0916505 -0.172 0.863271
## rankOrdLife_6C -0.0216681 0.1032775 -0.210 0.833821
## rankOrdLife_6D -0.1553012 0.1097932 -1.414 0.157227
## rankOrdLife_6E 0.0862898 0.1010645 0.854 0.393216
## rankOrdLife_6F -0.0386599 0.0856237 -0.452 0.651625
## rankOrdLife_6None -0.8917012 1.2834884 -0.695 0.487217
## c19perBeh01 0.0288094 0.0077193 3.732 0.000190 ***
## c19perBeh02 0.1201711 0.0093003 12.921 < 2e-16 ***
## c19perBeh03 0.0788599 0.0055050 14.325 < 2e-16 ***
## c19RCA01 0.0260745 0.0042053 6.200 5.69e-10 ***
## c19RCA02 0.0992844 0.0066545 14.920 < 2e-16 ***
## c19RCA03 -0.0494739 0.0045433 -10.889 < 2e-16 ***
## coronaClose_6 -0.1289673 0.0148836 -8.665 < 2e-16 ***
## genderMale -0.2324281 0.1075431 -2.161 0.030682 *
## genderFemale -0.2510462 0.1078575 -2.328 0.019940 *
## genderOther -0.0786837 0.1410792 -0.558 0.577034
## age 0.0534956 0.0043997 12.159 < 2e-16 ***
## eduPrimary education 0.1713024 0.1133528 1.511 0.130737
## eduGeneral secondary\neducation 0.0327627 0.1014647 0.323 0.746774
## eduVocational education 0.0236026 0.1020737 0.231 0.817136
## eduHigher\neducation 0.0640335 0.1006163 0.636 0.524511
## eduBachelors degree 0.0730171 0.1005059 0.726 0.467539
## eduMasters degree 0.0851634 0.1010244 0.843 0.399234
## eduPhD\ndegree 0.1313112 0.1036329 1.267 0.205134
## c19ProSo01 0.1370544 0.0054567 25.117 < 2e-16 ***
## c19ProSo02 0.0288981 0.0050372 5.737 9.71e-09 ***
## c19ProSo03 0.3251746 0.0049658 65.483 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.28 on 39028 degrees of freedom
## Multiple R-squared: 0.3345, Adjusted R-squared: 0.3333
## F-statistic: 284.2 on 69 and 39028 DF, p-value: < 2.2e-16Q3A: Clustering
set.seed(9999) # For reproducibility
external_sources <- read.csv("external_sources.csv")
external_sources$coded_country <- iconv(external_sources$coded_country, "ISO-8859-1", "UTF-8")external_sources_selected <- external_sources %>%
select(health_security, VoiceAccountability, GovernanceEffectiveness, RuleOfLaw) %>%
scale() # Standardizes the data# Perform k-means clustering
kmeans_result <- kmeans(external_sources_selected, centers = 2, nstart = 20) # you can adjust the number of clusters# calculate silhouette score
library(cluster)
external_sources = read.csv("external_sources.csv")
# gives the optimum number of clusters
i_silhouette_score = function(k){
km = kmeans(external_sources_selected, k, nstart = 20)
# ss gives all of the rows, which shows cluster, neighbour and sil_width
# which is the score
ss = silhouette(km$cluster, dist(external_sources_selected))
# average the sil scores, higher the score the btter the clustering
mean(ss[,3])
}
k = 2: 20
avg_sil = sapply(k, i_silhouette_score)
plot(k, avg_sil, type = 'b', xlab = 'Number of clusters', ylab = 'Average Silhouette Scores')
df = data.frame(k, avg_sil)
View(df)
df[which.max(df[,df$avg_sil])]## data frame with 0 columns and 19 rowsexternal_sources$cluster <- kmeans_result$cluster
View(external_sources)
south_africa_cluster <- external_sources[external_sources$coded_country == "South Africa", "cluster"]
similar_countries_cluster <- external_sources[which(external_sources$cluster == south_africa_cluster),]
print(similar_countries_cluster$coded_country)## [1] "Argentina" "Armenia"
## [3] "Australia" "Austria"
## [5] "Barbados" "Belgium"
## [7] "Bhutan" "Bulgaria"
## [9] "Canada" "Chile"
## [11] "Costa Rica" "Croatia"
## [13] "Cyprus" "Czech Republic"
## [15] "Denmark" "Estonia"
## [17] "Finland" "France"
## [19] "Georgia" "Germany"
## [21] "Greece" "Hungary"
## [23] "Iceland" "Ireland"
## [25] "Israel" "Italy"
## [27] "Japan" "Latvia"
## [29] "Liechtenstein" "Lithuania"
## [31] "Luxembourg" "Malaysia"
## [33] "Malta" "Mauritius"
## [35] "Monaco" "Netherlands"
## [37] "New Zealand" "Norway"
## [39] "Panama" "Poland"
## [41] "Portugal" "Romania"
## [43] "Samoa" "San Marino"
## [45] "Singapore" "Slovenia"
## [47] "South Africa" "South Korea"
## [49] "Spain" "Sweden"
## [51] "Switzerland" "Thailand"
## [53] "United Kingdom" "United States of America"
## [55] "Uruguay"Question 3B: P-Value
similar_countries <- c("Argentina", "Armenia", "Australia", "Austria", "Barbados",
"Belgium", "Bhutan", "Bulgaria", "Canada", "Chile", "Costa Rica",
"Croatia", "Cyprus", "Czech Republic", "Denmark", "Estonia",
"Finland", "France", "Georgia", "Germany", "Greece", "Hungary",
"Iceland", "Ireland", "Israel", "Italy", "Japan", "Latvia",
"Liechtenstein", "Lithuania", "Luxembourg", "Malaysia", "Malta",
"Mauritius", "Monaco", "Netherlands", "New Zealand", "Norway",
"Panama", "Poland", "Portugal", "Romania", "Samoa", "San Marino",
"Singapore", "Slovenia", "South Africa", "South Korea", "Spain",
"Sweden", "Switzerland", "Thailand", "United Kingdom",
"United States of America", "Uruguay")
cvbase_similar_countries <- cvbase %>%
filter(coded_country %in% similar_countries)
View(cvbase_similar_countries)Extract The Data Without Coded Country
cvbase_similar_cluster_withoutcodedcountry <- cvbase_similar_countries %>%
select(-coded_country)Identify Best Predictors In Similar Cluster Countries for c19ProSo01
cvbase_smilar_cluster_fit1 <- lm(cvbase_similar_cluster_withoutcodedcountry$c19ProSo01~., data = cvbase_similar_cluster_withoutcodedcountry)
summary(cvbase_smilar_cluster_fit1)##
## Call:
## lm(formula = cvbase_similar_cluster_withoutcodedcountry$c19ProSo01 ~
## ., data = cvbase_similar_cluster_withoutcodedcountry)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.4894 -0.5983 0.1270 0.7251 4.2190
##
## Coefficients: (5 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.7208064 0.3018919 2.388 0.016964 *
## isoFriends_inPerson 0.0099009 0.0034318 2.885 0.003917 **
## isoOthPpl_inPerson 0.0237658 0.0037690 6.306 2.91e-10 ***
## isoFriends_online 0.0095492 0.0033281 2.869 0.004117 **
## isoOthPpl_online 0.0043603 0.0031390 1.389 0.164822
## lone01 0.0362418 0.0093187 3.889 0.000101 ***
## lone02 -0.0189553 0.0082209 -2.306 0.021132 *
## lone03 0.0022157 0.0088066 0.252 0.801358
## happy -0.0009339 0.0047129 -0.198 0.842921
## lifeSat 0.0140573 0.0086614 1.623 0.104607
## MLQ 0.0368874 0.0060749 6.072 1.28e-09 ***
## bor01 0.0183070 0.0053476 3.423 0.000619 ***
## bor02 -0.0080294 0.0054236 -1.480 0.138767
## bor03 0.0202562 0.0048527 4.174 3.00e-05 ***
## consp01 0.0142833 0.0038888 3.673 0.000240 ***
## consp02 0.0024222 0.0040944 0.592 0.554132
## consp03 0.0032615 0.0031496 1.036 0.300425
## rankOrdLife_1B -0.0168172 0.0932175 -0.180 0.856833
## rankOrdLife_1C -0.0602187 0.1012780 -0.595 0.552124
## rankOrdLife_1D -0.0884626 0.1072949 -0.824 0.409674
## rankOrdLife_1E -0.1194453 0.0984919 -1.213 0.225239
## rankOrdLife_1F -0.0286569 0.0858266 -0.334 0.738463
## rankOrdLife_1None -0.5747026 0.2830399 -2.030 0.042319 *
## rankOrdLife_2B 0.0064775 0.0883029 0.073 0.941524
## rankOrdLife_2C -0.0330524 0.0979824 -0.337 0.735871
## rankOrdLife_2D -0.0647679 0.1041698 -0.622 0.534110
## rankOrdLife_2E -0.0928921 0.0955664 -0.972 0.331051
## rankOrdLife_2F -0.0145680 0.0872166 -0.167 0.867346
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 0.0375076 0.1003165 0.374 0.708487
## rankOrdLife_3C 0.0232018 0.1066649 0.218 0.827805
## rankOrdLife_3D -0.0135378 0.1119901 -0.121 0.903784
## rankOrdLife_3E -0.0410118 0.1033173 -0.397 0.691408
## rankOrdLife_3F 0.0083824 0.0926631 0.090 0.927922
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B 0.0223110 0.0846023 0.264 0.792001
## rankOrdLife_4C -0.0783414 0.0959762 -0.816 0.414360
## rankOrdLife_4D -0.0990938 0.1036378 -0.956 0.339003
## rankOrdLife_4E -0.1885101 0.0958213 -1.967 0.049158 *
## rankOrdLife_4F -0.1285636 0.0865341 -1.486 0.137371
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B 0.0426323 0.0843169 0.506 0.613128
## rankOrdLife_5C -0.0289933 0.0963292 -0.301 0.763431
## rankOrdLife_5D -0.0846799 0.1046757 -0.809 0.418537
## rankOrdLife_5E -0.1130440 0.0961974 -1.175 0.239955
## rankOrdLife_5F -0.0223181 0.0851519 -0.262 0.793249
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -0.0470011 0.0849515 -0.553 0.580083
## rankOrdLife_6C -0.1589303 0.0960077 -1.655 0.097857 .
## rankOrdLife_6D -0.1859528 0.1032520 -1.801 0.071720 .
## rankOrdLife_6E -0.3233111 0.0949727 -3.404 0.000664 ***
## rankOrdLife_6F -0.2647511 0.0806288 -3.284 0.001026 **
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 0.0812459 0.0086050 9.442 < 2e-16 ***
## c19perBeh02 0.0342694 0.0105740 3.241 0.001193 **
## c19perBeh03 -0.0298213 0.0060194 -4.954 7.31e-07 ***
## c19RCA01 0.0269360 0.0045513 5.918 3.29e-09 ***
## c19RCA02 -0.0019815 0.0071622 -0.277 0.782037
## c19RCA03 -0.0305175 0.0048169 -6.336 2.40e-10 ***
## coronaClose_6 -0.0663058 0.0166124 -3.991 6.59e-05 ***
## genderMale -0.2241368 0.1137985 -1.970 0.048895 *
## genderFemale -0.1357038 0.1142083 -1.188 0.234760
## genderOther -0.0288704 0.1489097 -0.194 0.846273
## age 0.0031009 0.0048071 0.645 0.518886
## eduPrimary education -0.2924537 0.1250069 -2.339 0.019317 *
## eduGeneral secondary\neducation -0.2230198 0.1144323 -1.949 0.051315 .
## eduVocational education -0.1576184 0.1151129 -1.369 0.170933
## eduHigher\neducation -0.2018900 0.1134066 -1.780 0.075049 .
## eduBachelors degree -0.2061813 0.1133778 -1.819 0.068994 .
## eduMasters degree -0.2172432 0.1138616 -1.908 0.056407 .
## eduPhD\ndegree -0.2361961 0.1164008 -2.029 0.042452 *
## c19ProSo02 0.1907449 0.0052567 36.286 < 2e-16 ***
## c19ProSo03 0.2982856 0.0054357 54.875 < 2e-16 ***
## c19ProSo04 0.0813866 0.0059355 13.712 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.173 on 26524 degrees of freedom
## Multiple R-squared: 0.3505, Adjusted R-squared: 0.3489
## F-statistic: 210.5 on 68 and 26524 DF, p-value: < 2.2e-16Identify Best Predictors In Similar Cluster Countries for c19ProSo02
cvbase_smilar_cluster_fit2 <- lm(cvbase_similar_cluster_withoutcodedcountry$c19ProSo02~., data = cvbase_similar_cluster_withoutcodedcountry)
summary(cvbase_smilar_cluster_fit2)##
## Call:
## lm(formula = cvbase_similar_cluster_withoutcodedcountry$c19ProSo02 ~
## ., data = cvbase_similar_cluster_withoutcodedcountry)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.4461 -0.7415 0.1816 0.8660 5.5495
##
## Coefficients: (5 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.059040 0.344228 -0.172 0.863822
## isoFriends_inPerson 0.009157 0.003913 2.340 0.019284 *
## isoOthPpl_inPerson -0.011401 0.004300 -2.652 0.008017 **
## isoFriends_online 0.007619 0.003795 2.008 0.044688 *
## isoOthPpl_online 0.010486 0.003578 2.930 0.003388 **
## lone01 0.021041 0.010627 1.980 0.047711 *
## lone02 -0.029547 0.009372 -3.153 0.001619 **
## lone03 0.026624 0.010039 2.652 0.008006 **
## happy 0.027966 0.005370 5.207 1.93e-07 ***
## lifeSat 0.050259 0.009871 5.092 3.57e-07 ***
## MLQ 0.049678 0.006924 7.175 7.44e-13 ***
## bor01 0.033512 0.006095 5.498 3.87e-08 ***
## bor02 0.007431 0.006184 1.202 0.229472
## bor03 0.014231 0.005534 2.572 0.010125 *
## consp01 -0.020599 0.004433 -4.647 3.39e-06 ***
## consp02 -0.018371 0.004667 -3.936 8.29e-05 ***
## consp03 0.011120 0.003590 3.097 0.001956 **
## rankOrdLife_1B -0.202139 0.106271 -1.902 0.057169 .
## rankOrdLife_1C -0.092041 0.115468 -0.797 0.425393
## rankOrdLife_1D 0.140624 0.122327 1.150 0.250329
## rankOrdLife_1E -0.188509 0.112289 -1.679 0.093205 .
## rankOrdLife_1F -0.395406 0.097822 -4.042 5.31e-05 ***
## rankOrdLife_1None -0.385373 0.322714 -1.194 0.232425
## rankOrdLife_2B -0.140439 0.100672 -1.395 0.163022
## rankOrdLife_2C -0.064252 0.111711 -0.575 0.565184
## rankOrdLife_2D 0.232829 0.118758 1.961 0.049943 *
## rankOrdLife_2E -0.038545 0.108958 -0.354 0.723525
## rankOrdLife_2F -0.320411 0.099417 -3.223 0.001271 **
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B -0.173444 0.114368 -1.517 0.129392
## rankOrdLife_3C -0.009202 0.121610 -0.076 0.939683
## rankOrdLife_3D 0.204770 0.127675 1.604 0.108762
## rankOrdLife_3E -0.105643 0.117792 -0.897 0.369802
## rankOrdLife_3F -0.322926 0.105628 -3.057 0.002236 **
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -0.149333 0.096452 -1.548 0.121571
## rankOrdLife_4C -0.002576 0.109425 -0.024 0.981218
## rankOrdLife_4D 0.200242 0.118155 1.695 0.090135 .
## rankOrdLife_4E -0.080474 0.109254 -0.737 0.461385
## rankOrdLife_4F -0.334465 0.098641 -3.391 0.000698 ***
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.158987 0.096126 -1.654 0.098152 .
## rankOrdLife_5C -0.030037 0.109826 -0.273 0.784478
## rankOrdLife_5D 0.186109 0.119338 1.560 0.118888
## rankOrdLife_5E -0.052129 0.109678 -0.475 0.634583
## rankOrdLife_5F -0.375176 0.097056 -3.866 0.000111 ***
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -0.145520 0.096851 -1.503 0.132974
## rankOrdLife_6C -0.040246 0.109465 -0.368 0.713129
## rankOrdLife_6D 0.145887 0.117723 1.239 0.215267
## rankOrdLife_6E -0.119256 0.108301 -1.101 0.270840
## rankOrdLife_6F -0.402212 0.091912 -4.376 1.21e-05 ***
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 0.045429 0.009823 4.625 3.77e-06 ***
## c19perBeh02 0.005497 0.012058 0.456 0.648480
## c19perBeh03 0.031257 0.006863 4.554 5.28e-06 ***
## c19RCA01 0.067262 0.005176 12.995 < 2e-16 ***
## c19RCA02 -0.003936 0.008166 -0.482 0.629823
## c19RCA03 0.047128 0.005488 8.587 < 2e-16 ***
## coronaClose_6 -0.044389 0.018944 -2.343 0.019126 *
## genderMale 0.200199 0.129747 1.543 0.122844
## genderFemale 0.114638 0.130212 0.880 0.378652
## genderOther 0.035327 0.169774 0.208 0.835167
## age 0.020079 0.005479 3.665 0.000248 ***
## eduPrimary education -0.224631 0.142530 -1.576 0.115032
## eduGeneral secondary\neducation -0.372096 0.130455 -2.852 0.004344 **
## eduVocational education -0.465292 0.131215 -3.546 0.000392 ***
## eduHigher\neducation -0.231420 0.129296 -1.790 0.073491 .
## eduBachelors degree -0.195012 0.129266 -1.509 0.131410
## eduMasters degree -0.116212 0.129822 -0.895 0.370709
## eduPhD\ndegree -0.022112 0.132720 -0.167 0.867682
## c19ProSo01 0.247941 0.006833 36.286 < 2e-16 ***
## c19ProSo03 0.311987 0.006253 49.896 < 2e-16 ***
## c19ProSo04 0.034395 0.006788 5.067 4.07e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.338 on 26524 degrees of freedom
## Multiple R-squared: 0.342, Adjusted R-squared: 0.3403
## F-statistic: 202.8 on 68 and 26524 DF, p-value: < 2.2e-16Identify Best Predictors In Similar Cluster Countries for c19ProSo03
cvbase_smilar_cluster_fit3 <- lm(cvbase_similar_cluster_withoutcodedcountry$c19ProSo03~., data = cvbase_similar_cluster_withoutcodedcountry)
summary(cvbase_smilar_cluster_fit3)##
## Call:
## lm(formula = cvbase_similar_cluster_withoutcodedcountry$c19ProSo03 ~
## ., data = cvbase_similar_cluster_withoutcodedcountry)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.4544 -0.7060 0.1549 0.7487 5.9139
##
## Coefficients: (5 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -7.158e-01 3.232e-01 -2.215 0.026776 *
## isoFriends_inPerson 5.549e-03 3.674e-03 1.510 0.130980
## isoOthPpl_inPerson 1.286e-02 4.037e-03 3.186 0.001445 **
## isoFriends_online -6.225e-03 3.563e-03 -1.747 0.080646 .
## isoOthPpl_online 2.015e-02 3.358e-03 5.999 2.01e-09 ***
## lone01 5.147e-03 9.978e-03 0.516 0.605969
## lone02 -4.192e-03 8.801e-03 -0.476 0.633885
## lone03 3.105e-02 9.425e-03 3.294 0.000989 ***
## happy 7.643e-05 5.045e-03 0.015 0.987914
## lifeSat 2.171e-02 9.271e-03 2.342 0.019188 *
## MLQ -1.052e-03 6.507e-03 -0.162 0.871545
## bor01 -2.355e-03 5.726e-03 -0.411 0.680840
## bor02 1.090e-02 5.806e-03 1.877 0.060549 .
## bor03 9.432e-03 5.196e-03 1.815 0.069503 .
## consp01 -9.765e-03 4.163e-03 -2.345 0.019012 *
## consp02 -2.097e-02 4.381e-03 -4.786 1.71e-06 ***
## consp03 6.550e-03 3.371e-03 1.943 0.052045 .
## rankOrdLife_1B 1.337e-02 9.979e-02 0.134 0.893387
## rankOrdLife_1C 1.678e-01 1.084e-01 1.548 0.121716
## rankOrdLife_1D -2.537e-03 1.149e-01 -0.022 0.982380
## rankOrdLife_1E 7.737e-02 1.054e-01 0.734 0.463047
## rankOrdLife_1F 1.729e-01 9.187e-02 1.883 0.059778 .
## rankOrdLife_1None 6.014e-01 3.030e-01 1.985 0.047160 *
## rankOrdLife_2B 7.023e-02 9.452e-02 0.743 0.457494
## rankOrdLife_2C 2.755e-01 1.049e-01 2.627 0.008608 **
## rankOrdLife_2D 7.645e-02 1.115e-01 0.686 0.492982
## rankOrdLife_2E 1.798e-01 1.023e-01 1.758 0.078813 .
## rankOrdLife_2F 3.041e-01 9.334e-02 3.258 0.001123 **
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 6.284e-02 1.074e-01 0.585 0.558416
## rankOrdLife_3C 1.403e-01 1.142e-01 1.229 0.219016
## rankOrdLife_3D 1.980e-02 1.199e-01 0.165 0.868824
## rankOrdLife_3E 8.261e-02 1.106e-01 0.747 0.455118
## rankOrdLife_3F 2.180e-01 9.918e-02 2.197 0.027997 *
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B -2.983e-02 9.056e-02 -0.329 0.741871
## rankOrdLife_4C 1.725e-01 1.027e-01 1.679 0.093192 .
## rankOrdLife_4D -6.870e-02 1.109e-01 -0.619 0.535789
## rankOrdLife_4E -2.088e-02 1.026e-01 -0.204 0.838676
## rankOrdLife_4F 1.491e-01 9.263e-02 1.609 0.107536
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B 1.837e-02 9.026e-02 0.204 0.838692
## rankOrdLife_5C 2.138e-01 1.031e-01 2.074 0.038116 *
## rankOrdLife_5D 6.195e-02 1.121e-01 0.553 0.580380
## rankOrdLife_5E 1.283e-01 1.030e-01 1.246 0.212692
## rankOrdLife_5F 2.744e-01 9.114e-02 3.011 0.002610 **
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B -6.122e-03 9.094e-02 -0.067 0.946323
## rankOrdLife_6C 1.285e-01 1.028e-01 1.251 0.211086
## rankOrdLife_6D -1.190e-01 1.105e-01 -1.077 0.281615
## rankOrdLife_6E -7.531e-02 1.017e-01 -0.741 0.458965
## rankOrdLife_6F 1.346e-01 8.632e-02 1.559 0.119040
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 5.794e-03 9.227e-03 0.628 0.530057
## c19perBeh02 -3.019e-02 1.132e-02 -2.667 0.007656 **
## c19perBeh03 1.214e-02 6.446e-03 1.884 0.059628 .
## c19RCA01 -2.079e-03 4.875e-03 -0.426 0.669818
## c19RCA02 -2.772e-02 7.665e-03 -3.616 0.000300 ***
## c19RCA03 -1.207e-02 5.160e-03 -2.340 0.019303 *
## coronaClose_6 -2.822e-02 1.779e-02 -1.586 0.112670
## genderMale 3.737e-02 1.218e-01 0.307 0.759057
## genderFemale 5.043e-02 1.223e-01 0.413 0.679974
## genderOther 7.408e-02 1.594e-01 0.465 0.642133
## age -9.227e-02 5.115e-03 -18.041 < 2e-16 ***
## eduPrimary education 1.651e-01 1.338e-01 1.234 0.217270
## eduGeneral secondary\neducation 2.084e-01 1.225e-01 1.701 0.088982 .
## eduVocational education 2.323e-01 1.232e-01 1.885 0.059399 .
## eduHigher\neducation 1.638e-01 1.214e-01 1.349 0.177205
## eduBachelors degree 2.472e-01 1.214e-01 2.037 0.041692 *
## eduMasters degree 2.432e-01 1.219e-01 1.995 0.046037 *
## eduPhD\ndegree 3.565e-01 1.246e-01 2.861 0.004223 **
## c19ProSo01 3.418e-01 6.229e-03 54.875 < 2e-16 ***
## c19ProSo02 2.750e-01 5.512e-03 49.896 < 2e-16 ***
## c19ProSo04 3.109e-01 6.084e-03 51.109 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.256 on 26524 degrees of freedom
## Multiple R-squared: 0.4363, Adjusted R-squared: 0.4349
## F-statistic: 301.9 on 68 and 26524 DF, p-value: < 2.2e-16Identify Best Predictors In Similar Cluster Countries for c19ProSo04
cvbase_smilar_cluster_fit4 <- lm(cvbase_similar_cluster_withoutcodedcountry$c19ProSo04~., data = cvbase_similar_cluster_withoutcodedcountry)
summary(cvbase_smilar_cluster_fit4)##
## Call:
## lm(formula = cvbase_similar_cluster_withoutcodedcountry$c19ProSo04 ~
## ., data = cvbase_similar_cluster_withoutcodedcountry)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.5806 -0.5900 0.1365 0.7542 5.5145
##
## Coefficients: (5 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.4203033 0.3112231 -1.350 0.176871
## isoFriends_inPerson -0.0072276 0.0035379 -2.043 0.041073 *
## isoOthPpl_inPerson -0.0003532 0.0038881 -0.091 0.927615
## isoFriends_online 0.0182880 0.0034294 5.333 9.75e-08 ***
## isoOthPpl_online 0.0010538 0.0032359 0.326 0.744677
## lone01 -0.0278099 0.0096072 -2.895 0.003798 **
## lone02 0.0670697 0.0084652 7.923 2.41e-15 ***
## lone03 -0.0073869 0.0090781 -0.814 0.415819
## happy -0.0094178 0.0048579 -1.939 0.052553 .
## lifeSat 0.0198783 0.0089281 2.226 0.025990 *
## MLQ 0.0057923 0.0062664 0.924 0.355320
## bor01 -0.0215417 0.0055121 -3.908 9.33e-05 ***
## bor02 0.0132142 0.0055905 2.364 0.018101 *
## bor03 0.0061272 0.0050038 1.224 0.220778
## consp01 0.0216056 0.0040076 5.391 7.06e-08 ***
## consp02 0.0092371 0.0042203 2.189 0.028626 *
## consp03 -0.0129948 0.0032458 -4.004 6.26e-05 ***
## rankOrdLife_1B 0.0368727 0.0960915 0.384 0.701186
## rankOrdLife_1C 0.1234948 0.1043987 1.183 0.236854
## rankOrdLife_1D 0.0957057 0.1106031 0.865 0.386878
## rankOrdLife_1E 0.4002398 0.1015018 3.943 8.06e-05 ***
## rankOrdLife_1F 0.3150663 0.0884520 3.562 0.000369 ***
## rankOrdLife_1None 0.1263311 0.2917888 0.433 0.665052
## rankOrdLife_2B 0.0739827 0.0910245 0.813 0.416353
## rankOrdLife_2C 0.1229902 0.1010009 1.218 0.223344
## rankOrdLife_2D 0.0673687 0.1073817 0.627 0.530419
## rankOrdLife_2E 0.2440669 0.0985034 2.478 0.013228 *
## rankOrdLife_2F 0.2334383 0.0898944 2.597 0.009415 **
## rankOrdLife_2None NA NA NA NA
## rankOrdLife_3B 0.0004744 0.1034099 0.005 0.996340
## rankOrdLife_3C 0.1201360 0.1099514 1.093 0.274567
## rankOrdLife_3D 0.0089981 0.1154432 0.078 0.937873
## rankOrdLife_3E 0.2946544 0.1064879 2.767 0.005661 **
## rankOrdLife_3F 0.2421559 0.0955087 2.535 0.011237 *
## rankOrdLife_3None NA NA NA NA
## rankOrdLife_4B 0.0182885 0.0872110 0.210 0.833900
## rankOrdLife_4C 0.0401502 0.0989365 0.406 0.684879
## rankOrdLife_4D -0.0931742 0.1068337 -0.872 0.383138
## rankOrdLife_4E 0.1381153 0.0987794 1.398 0.162059
## rankOrdLife_4F -0.0288749 0.0892058 -0.324 0.746176
## rankOrdLife_4None NA NA NA NA
## rankOrdLife_5B -0.0049496 0.0869172 -0.057 0.954589
## rankOrdLife_5C -0.0047829 0.0992996 -0.048 0.961584
## rankOrdLife_5D -0.1504688 0.1079006 -1.395 0.163175
## rankOrdLife_5E 0.1170135 0.0991635 1.180 0.238009
## rankOrdLife_5F -0.0524715 0.0877770 -0.598 0.549991
## rankOrdLife_5None NA NA NA NA
## rankOrdLife_6B 0.0076730 0.0875714 0.088 0.930180
## rankOrdLife_6C 0.0042764 0.0989731 0.043 0.965536
## rankOrdLife_6D -0.1190975 0.1064397 -1.119 0.263184
## rankOrdLife_6E 0.1213572 0.0979196 1.239 0.215225
## rankOrdLife_6F -0.0196407 0.0831317 -0.236 0.813233
## rankOrdLife_6None NA NA NA NA
## c19perBeh01 0.0363807 0.0088824 4.096 4.22e-05 ***
## c19perBeh02 0.1616897 0.0108569 14.893 < 2e-16 ***
## c19perBeh03 0.0950594 0.0061804 15.381 < 2e-16 ***
## c19RCA01 0.0016619 0.0046948 0.354 0.723346
## c19RCA02 0.1128538 0.0073504 15.353 < 2e-16 ***
## c19RCA03 -0.0326091 0.0049651 -6.568 5.21e-11 ***
## coronaClose_6 -0.1432177 0.0171071 -8.372 < 2e-16 ***
## genderMale -0.0587263 0.1173154 -0.501 0.616667
## genderFemale -0.0947026 0.1177315 -0.804 0.421176
## genderOther 0.1096229 0.1534998 0.714 0.475137
## age 0.0398695 0.0049493 8.056 8.24e-16 ***
## eduPrimary education 0.0379293 0.1288745 0.294 0.768522
## eduGeneral secondary\neducation -0.0980370 0.1179676 -0.831 0.405953
## eduVocational education -0.0434845 0.1186662 -0.366 0.714037
## eduHigher\neducation -0.0776007 0.1169094 -0.664 0.506844
## eduBachelors degree -0.0611924 0.1168803 -0.524 0.600598
## eduMasters degree -0.0112509 0.1173805 -0.096 0.923640
## eduPhD\ndegree 0.0255719 0.1199991 0.213 0.831250
## c19ProSo01 0.0864829 0.0063072 13.712 < 2e-16 ***
## c19ProSo02 0.0281173 0.0055490 5.067 4.07e-07 ***
## c19ProSo03 0.2883324 0.0056416 51.109 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.21 on 26524 degrees of freedom
## Multiple R-squared: 0.3415, Adjusted R-squared: 0.3398
## F-statistic: 202.3 on 68 and 26524 DF, p-value: < 2.2e-16