Data Analysis on World Happiness Report
World happiness report
Data Background
Data in the World Happiness Report tries to explain the Happiness Score with factors including Country, Region, Economy, Social Support, Health, Freedom, Absence of Corruption, and Generosity.
- Can be more accurately described as Life Evaluations or Subjective Well-Being
- First World Happiness Report was suggested at UN Assembly by the country of Bhutan
- Primary data in report is based on Gallup World Polls
Why is it Important?
- Can reorient government and company objectives to prioritize human happiness and well-being
- It changes the metric for cost-benefit analysis to include happiness instead of mostly monetary value
- Can affect government and company initiatives
- Using Happiness (or Subjective Well-Being) as a metric, we can try to increase it
Dataset Information: Method
- Based mostly on Gallup World Polls.
- Gallup samples each country to represent about 98% of the population.
- In countries where phones are widely available, Gallup samples numbers and conducts interviews over the phone (~30 minutes). In countries where phones are not prevalent, then Gallup conducts in-person interviews, usually for about an hour.
- For most countries, the number of interviews was at least 1000.
Dataset Information: Features
- Happiness Score - Gallup asked respondents to evaluate their current life as a whole using the mental image of a ladder, with the best possible life for them as a 10 and worst possible as a 0.
- Economy - based on GDP per capita is in terms of Purchasing Power Parity (PPP). The equation uses the natural log of GDP per capita.
- Social Support - is the national average of the binary responses (either 0 or 1) to the Gallup World Poll (GWP) question “If you were in trouble, do you have relatives or friends you can count on to help you whenever you need them, or not?”
- Health - based on life expectancy at birth.
- Freedom - to make life choices is the national average of binary responses to the GWP question “Are you satisfied or dissatisfied with your freedom to choose what you do with your life?”
- Absence of Corruption - “Is corruption widespread throughout the government or not?” and “Is corruption widespread within businesses or not?” Where data for government corruption are missing, the perception of business corruption is used as the overall corruption-perception measure.
- Generosity - is the residual of regressing the national average of GWP responses to the question “Have you donated money to a charity in the past month?” on GDP per capita.
Data Analysis Objective
- Are the factors in the analysis robust? (understandable curves and outliers?)
- Do the factors explain the Happiness Score?
- Value: use these factors to increase Happiness
Conclusion
- The dataset shows that these factors are robust.
- The dataset shows that these factors do explain the Happiness Score.
- Economy (0.74), Health (0.73), Social Support (0.63), Freedom (0.57), Absence of Corruption (0.41), Generosity (0.09)
Recommendations
- My recommendation is for government and companies to start using the Happiness Score as a metric
- Actionable recommendations include:
- Creating a social support groups, awareness of available resources (increase Social Support)
- More encouragement of preventive medical appointments
- Companies could offer more choices to employees, for example, once in a while, they can do a project reshuffle, where employees could choose from a list of projects the one they want to work on.
- Also, employees preference for projects can affect its priority
Next Steps
- Continue to explore relationships between the factors
- Cut into subgroups and perform tests to see if there are differences between the groups (ie. if we cut the Happiness Score into greater than 7.0 as Highly Happy and less than 3.5 as Highly Unhappy, can we see a difference when we compare them?)
- Experiment for causal effects (ie. if we made changes to increase Health, would it make people happier?)
The skills I demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.
Data Analysis Code
About Author
Tam Trinh
View all posts by Tam Trinh >Related Articles
Leave a Comment
No comments found.