RPubs link information

• Rpubs link comes here :

Introduction

• It is a common notion around the world that people with more education tend to have more savings compared to people with lower education level
  
• In this presentation we will analyze the saving and borrowing habits of 1002 Australian citizens based on their education levels, namely, Primary or less, Secondary and Tertiary or above.
• Each individual is identified by a unique identifier number called as “Gallup World Poll identifier”.
• To achieve results of our analysis, we will use various comparison tables, summary statistics and plots.

Problem Statement

• We will analyze people with higher education have more savings and if the monthly income differs based on the level of education.
• We will use various comparison tables, summary statistics and plots to achieve the results of our analysis.

Data - Source

• The dataset used for our analysis has been sourced from www.microdata.worldbank.org.
• For our analysis, only Australian citizen sample has been considered.

Data - Overview

• The dataset contains the borrowing/saving habits of 1002 Australians.
• It contains 63 variables.
• Each individual is uniquely identified by an identifier called as “Gallup World Poll identifier”.
• The education level of an individual in the sample is divided into 3 categories, namely, Primary or less, Secondary and Tertiary or above and is described by the variable “Respondent education level”.
• Monthly income of each individual is goven in the variable Month_inc. The income is in Dollars($).
• Variable “Saved in the past year” gives information if an individual has saved in the past year(Yes or No) and variable “Borrowed in the past year” gives information if an individual has borrowed in the past year(Yes or No).

Descriptive Statistics and Visualisation

• Let us first import the data into R

financial_habits<-read.csv("aus_saving.csv")

• Renaming the Education Levels in the dataset

financial_habits$Respondent.education.level<- factor(financial_habits$Respondent.education.level,
                                                     levels = c("completed tertiary or more",
                                                     "secondary", "completed primary or less")
                                                     ,labels = c("Tertiary or above","Secondary",
                                                     "Primary or less"))

• Removing those rows which do not have education level in the dataset and then dividing the dataset based on Education Level

financial_habits <- financial_habits %>% filter(Respondent.education.level=="Primary or less" |  Respondent.education.level=="Secondary" | Respondent.education.level=="Tertiary or above")

primary <- financial_habits %>% filter(Respondent.education.level=="Primary or less")
secondary <- financial_habits %>% filter(Respondent.education.level=="Secondary")
tertiary <- financial_habits %>% filter(Respondent.education.level=="Tertiary or above")

Summary Statistics for the Monthly income of individuals for each Education Level

• Below are the summary statistics for the Monthly income of individuals

financial_habits %>% group_by(Respondent.education.level) %>% summarise(Mean = mean(Month_inc, na.rm = TRUE),
                                           n = n(),
                                           Missing = sum(is.na(Month_inc))) -> table1
knitr::kable(table1)

Box plot to show the difference in the monthly income of individuals based on their education levels

monthly_inc.plot<- ggplot(financial_habits, aes(x=Respondent.education.level,y=Month_inc,
fill=Respondent.education.level))+geom_boxplot() + 
labs(title="Boxplot of Monthly Income based on education level", y="Monthly Income ($)",
x="Education Level")

monthly_inc.plot

Count of individuals who have saved in past one year based on education level

• People with Primary or less education

primary_totalcount <- primary %>% summarise(n())

primary_saved <- primary %>% filter(Saved.in.the.past.year=="yes")

primary_saved_count <- primary_saved %>% summarise(n())

table_primary <- matrix(c(primary_saved_count,primary_totalcount),ncol=2)
colnames(table_primary) <- c("Count of people who have Saved","Total Count of people")
rownames(table_primary) <- c("")
table_primary

##  Count of people who have Saved Total Count of people
##  35                             51

Count of individuals who have saved contd…

• People with Secondary education

secondary_totalcount <- secondary %>% summarise(n())

secondary_saved <- secondary %>% filter(Saved.in.the.past.year=="yes")

secondary_saved_count <- secondary_saved %>% summarise(n())

table_secondary <- matrix(c(secondary_saved_count,secondary_totalcount),ncol=2)
colnames(table_secondary) <- c("Count of people who have Saved","Total Count of people")
rownames(table_secondary) <- c("")
table_secondary

##  Count of people who have Saved Total Count of people
##  460                            586

Count of individuals who have saved contd…

• People with Tertiary or above education

tertiary_totalcount <- tertiary %>% summarise(n())

tertiary_saved <- tertiary %>% filter(Saved.in.the.past.year=="yes")

tertiary_saved_count <- tertiary_saved %>% summarise(n())

table_tertiary <- matrix(c(tertiary_saved_count,tertiary_totalcount),ncol=2)
colnames(table_tertiary) <- c("Count of people who have Saved","Total Count of people")
rownames(table_tertiary) <- c("")
table_tertiary

##  Count of people who have Saved Total Count of people
##  311                            348

Discussion

• Based on our analysis we conclude that there is a difference in the monthly income based on the education level.
• Individuals with Tertiary or above education have more monthly income compared to individuals with primary or less.
• We also conclude that Savings is maximum among individuals with Tertiary or above education with 89.36% (311 out of 348) and least among individuals with Primary or less education with 68.63% (35 out of 51).
• We finally conclude from our findings that individuals with higher education level tend to save more and have a higher monthly income.

References

• The data has been sourced from www.microdata.worldbank.org.