The Effect of Various Factors on World Happiness Score

The World Happiness Report (2015) is a survey of the state of world happiness. The report continues to gain world recognition as governments and organizations use happiness indicators to inform their policy-making decisions. The happiness scores and rankings use data from the Gallup World Poll. The scores are based on answers to the main life evaluation question asked in the poll.

First, I will look at the Happiness Score by Region. Following that, I will look at Health Life Expectancy, Freedom, and Economy GDP Per Capita by Region, while still looking at the Happiness Score. Following that, I will run some Zelig model plots.

Getting the data ready

library(readr)
happiness2015<-read_csv("C:/Users/wroni/OneDrive/Documents/QC MADASR/SOC 712/happiness2015.csv")
library(sjlabelled)
happiness2015_2<-sjlabelled::remove_all_labels(happiness2015)

head(happiness2015_2)

I imported the dataset and removed the labels. Here is a quick preview of the dataset.

World Happiness Score by Region

library(ggplot2)
library(viridis)

ggplot(happiness2015_2,aes(x=reorder(Region,Happiness.Score),y=Happiness.Score,fill=Happiness.Score))+geom_bar(stat = "identity")+scale_fill_viridis(name = "Happiness Score", option = "A")+coord_flip()+labs(title = 'World Happiness Score by Region')+
  theme_minimal()

This plot shows that Western Europe, Sub-Saharan Africa, and Central + Esatern Europe regions of the world have the highest Happiness Score. The bars show the variations in the scores as well. It is interesting to note that North America, our current residency, has low Happiness Score.

Health Life Expectancy by Region

ggplot(happiness2015_2, aes(x = Region, y = Health..Life.Expectancy., fill=Happiness.Score)) + geom_bar(stat = "identity") + theme(axis.text.x = element_text(angle = 90)) +  ggtitle("Health Life Expectancy by Region")

The previous plot showed the regions that has the higest and lowest Happiness Score and this plot attempts to explain the score by looking at Health Life Expectancy. The top 3 highest regions with the highest Happiness Score also has the highest Health Life Expectancy. North America has the lowest Happiness Score and lowest Health Life Expectancy. The bars show the variation in Hapiness Scores.

Freedom by Region

ggplot(happiness2015_2, aes(x = Region, y = Freedom, fill=Happiness.Score)) + geom_bar(stat = "identity") + theme(axis.text.x = element_text(angle = 90)) +  ggtitle("Freedom by Region")

This plot attempts to explain the Happiness Score by looking at Freedom of each Region. Again, the top 2 highest regions with the highest Happiness Score also has the highest Freedom. Latin America and Caribbean has the 3rd highest Freedom while Central and Eastern Europe has the 4th highest Freedom. Again, North America has the lowest Happiness Score and lowest Freedom. The bars show the variation in Hapiness Scores.

Economy by Region

ggplot(happiness2015_2, aes(x = Region, y = Economy..GDP.per.Capita., fill=Happiness.Score)) + geom_bar(stat = "identity") + theme(axis.text.x = element_text(angle = 90)) +  ggtitle("Economy by Region")

This plot attempts to explain the Happiness Score by looking at Economcy of each Region. Western Europe has the highest Happiness Score and Economcy while Latin American + Caribbean and Centra + Eastern Europe has the 2nd and 3rd highest Economy. Again, North America has the lowest Happiness Score and lowest Economy. The bars show the variation in Hapiness Scores.

Zelig simulation

library(Zelig)

m1 <- zelig(Happiness.Score ~ Region + Health..Life.Expectancy. + Freedom + Economy..GDP.per.Capita., model = "poisson", data = happiness2015_2, cite = F)

l.range = min(happiness2015_2$Health..Life.Expectancy.):max(happiness2015_2$Health..Life.Expectancy.)
x <- setx(m1, Health..Life.Expectancy. = l.range)
s <- sim(m1, x = x)
ci.plot(s)

This Zelig simulation plot shows that there is a positive correlation between Health Life Expectancy and Happiness Score. As Health Life Expectancy increaes, so does Happiness Score.

m1 <- zelig(Happiness.Score ~ Region + Health..Life.Expectancy. + Freedom + Economy..GDP.per.Capita., model = "poisson", data = happiness2015_2, cite = F)

e.range = min(happiness2015_2$Economy..GDP.per.Capita.):max(happiness2015_2$Economy..GDP.per.Capita.)
x <- setx(m1, Economy..GDP.per.Capita. = e.range)
s <- sim(m1, x = x)
ci.plot(s)

This Zelig simulation plot shows that there is a positive correlation between Economy and Happiness Score. As Economy increaes, so does Happiness Score.

Conclusion

The series of plots and Zelig simulation shows that World Happiness Score is affected by various factors. First, I showed that happiness varies by different regions of the world. Then, I looked at each region and showed that the happiness will vary depending on life expectancy, freedom, and economy. Finally, I ran Zelig simulations using poisson model to show that there is a positive correlation between happiness and life expectancy, and happiness and economy.