Happiness: What influences it?
The World Happiness Report is a survey of the state of global happiness. Data for this survey is collected via the Gallup World Poll and the report is published yearly by the Sustainable Development Solutions Network. The Cantril ladder survey is the basis for the national happiness ranking. Representatives of each country are asked to think of a ladder, with the best possible life for them being a 10, and the worst possible life being a 0. They are then asked to rate their own current lives on that 0 to 10 scale. The report correlates the results with various life factors.
In the happiness reports, experts in fields including economics, psychology, survey analysis, and national statistics, describe how measurements of well-being can be used effectively to assess the progress of nations, and other topics.
I have performed an Exploratory Data Analysis on the World Happiness Report datasets corresponding to the years 2015 to 2019 to draw insight into the factors that make people happy and the happiest and saddest countries across the years. Each dataset has the following columns of which I have given a brief description.
1. Country: Name of the country
2. Region: This breaks the country into regions according to the continent.
3. Happiness rank: The rank of each country’s happiness from 1–156 based on the world happiness score.
4. Happiness score: The score of each country is based on a happiness scale from one to ten.
5. GDP per capita: which gives us insight into how well a country is doing economically.
6. Social support: The physical and emotional comfort given to us by our family, friends, co-workers, and others. Also gives us insight into how much a country values family.
7. Health (Life expectancy): based on access, and quality of health care.
8. Freedom to make life choices: An individual’s opportunity and autonomy to perform an action selected from at least two available options, unconstrained by external parties
9. Generosity: based on how generous the people are in the given country.
10. Perceptions of corruption: An index that scores countries on how corrupt their governments are believed to be.
Reading the dataset
DATA CLEANING/WRANGLING
Since I had 5 different datasets to be merged, I started by changing the column names for consistency across the datasets. Redundant columns were dropped and a new column for the year was included for each dataset. Finally, using the merge and Concat function, the 5 datasets were merged into one. The code for this process can be viewed in my GitHub account.
EXPLORATORY DATA ANALYSIS
1. Happiest countries over the years
Using seaborn and the subplot function, the top 10 happiest countries across the 5 year period were visualized.
From the plot above, most countries maintained their position in the top 10 across the 5 year period. They also maintained a score of around 7. In 2017, there was a short dip in all the countries. There was a decline in Switzerland’s position whereas Finland jumped from the 5th position in 2017 to 1st position in 2018 and 2019. The Finns are known to have high incomes, health care for all, a top-notch education system, and having the cleanest air in the world.
2. Least happy countries over the years
The 10 countries with the least happiness score are given below.
For all the years, the happiness score for these countries was not up to the average of the entire scores (5.3). The scores lied between 0 and 4. Afghanistan which managed to escape the table in 2017 and 2018 returned in 2019. This could be due to the military operations between Afghan and US government forces and the Taliban which intensified in 2019, causing more than 8,000 civilian casualties between January 1 and September 30. Zimbabwe which was not part of the least 10 countries in 2015–2018 surfaced in 2019. In January 2019 there was a huge hike in the price of fuel which led to a nationwide protest which was met with a furious militarized response thereby throwing the country into chaos. This could explain the reason Zimbabwe was listed among the least happy countries in 2019.
In summary, instability, chaos, and war in a country tend to cause a low happiness score.
3. Correlating features with the happiness score
In this section, I’ll be checking for any significant linear relationship between Happiness Score and GDP, family support, perception of corruption, life expectancy, and freedom to make decisions across the years. To do this, I have used a heatmap. Heatmap plots were done for each year which can be viewed here. For the combined dataset, a separate heatmap was plotted.
3a. Relationship between GDP and Happiness score
From the heatmap, the correlation coefficient between GDP per capita and Happiness score is 0.79 in all the 5 years indicating a strong positive relationship between them. The correlation coefficient between the GDP and the happiness score was the highest amongst the other factors which implies that the GDP is one of the top priorities in determining how happy people are in a nation. The GDP indicates how well a country is faring economically. Countries having positive economic growth rates tend to have happier people because the growth of the economy leads to higher income and hence a better standard of living.
3b. Relationship between Life expectancy and Happiness score
The correlation coefficient between the life expectancy and happiness score is 0.74 indicating a similarly strong positive relationship between them. This value follows closely that of the GDP meaning that it is also a top factor in the happy state of a country. Life expectancy, the average amount of time a human is expected to live, is one of the key metrics for analyzing the health of the population of a country. Knowing that one has easy access to quality health care and thus chances of a long life abound, will cause one to be happy.
3c. Relationship between freedom to make life choices and Happiness Score
The correlation coefficient between freedom and happiness score is exactly 0.55 in all 5 years indicating a moderately positive relationship between them. This factor will vary in different countries because of the underlying traditions that have been accepted in those countries. For instance, a citizen of a country that accepts dictatorship rule will see nothing wrong with it and is happy in his country whereas a person coming from a democratic nation will react otherwise. The perception of freedom is relative, however, it is significant in determining the happiness score of a nation.
3d. Relationship between the perception of corruption and Happiness score
The correlation coefficient between the perception of corruption and happiness score is 0.41 in all five years. This indicates a weak positive relationship between the perception of corruption and the happiness score of a country. That is, the happiness of a nation does not lie solely on how the people perceive the government to be: either corrupt or not.
3e. Relationship between Generosity and Happiness score
The correlation coefficient is observed to be 0.14 which indicates a very weak positive relationship. The linear change between them is insignificant. This implies that a nation does not depend on how generous its citizens are to be happy.
3f. Relationship between Social Support and Happiness score
The correlation value is observed to be 0.64 which indicates a moderately strong positive relationship. Social support indicates the physical and emotional comfort given by family, friends, co-workers, etc. This correlation value implies that a nation that places value on the family will tend to have happy citizens since these are the people everyone deals with every day.
From the correlation plot, we concluded that GDP and life expectancy with correlation coefficients of 0.79 and 0.74 respectively had the most influence on the happiness score.
