Effects of Covid-19 on the World Happiness Report

Authors: Sean Lim (Project Lead), Binze Li, Nicole Ju, Christine Shen, Paige Lee

Introduction

The World Happiness Report 2021 focuses on the effects of COVID-19 and how people all over the world have fared. Our aim was two-fold, first to focus on the effects of COVID-19 on the structure and quality of people’s lives, and second to describe and evaluate how governments all over the world have dealt with the pandemic. In particular, we try to explain why some countries have done so much better than others.

In this dataset, it contains the mortality data due to various factors across the globe in different countries from the Ninth World Happiness report (2021). The World Happiness Report 2021 focuses on the effects of COVID-19 and how people all over the world have fared. Our goal is to try to figure out why some countries are doing better than others in terms of COVID-19 Deaths.

Exploratory Data Analysis

This visualization displays the countries with the top 10 healthy life expectancy scores and the gender of their leaders. Among these 12 countries (some countries had tied healthy life expectancy scores), Singapore is the only one that has a female leader. Singapore also has the highest healthy life expectancy score out of all countries in the dataset. For context, there are only roughly 20 countries that have a female leader out of 195 total countries in the world. 20 out of 195 is roughly 10%, and this proportion aligns with the sample of top 10 healthy life expectancy scores, where only one country out of 12 has a female leader. Since there is only one country that has a female leader among the 12 countries with the top 10 healthy life expectancy scores, it is difficult to draw a conclusion since there already exists many fewer female leaders in the world anyways.

This visualization explores the relationship between median age and healthy life expectancy score by geographic region. There appears to be a correlation between median age and healthy life expectancy score. Countries with lower median ages tend to also have lower healthy life expectancy scores. Countries with higher median ages tend to also have higher healthy life expectancy scores. It makes sense that populations with younger median ages possess this attribute because more of their people die at a younger age (lower healthy life expectancy score), and vice versa. We were also curious about the breakdown of this trend. Which countries have lower median ages and life expectancies? Which countries have higher median ages and life expectancies? Countries in the Sub-Saharan Africa region tend to have lower median ages and healthy life expectancy scores. Countries in Latin America, the Caribbean, East Asia, the Middle East, and North Africa tend to have modest median ages and healthy life expectancy scores. Countries in Central and Eastern Europe, North America, Australia/New Zealand, Russia, and Western Europe tend to have higher median ages and healthy life expectancy scores. To further investigate the geographic breakdown of the relationship between median age and healthy life expectancy scores, a next step would be to research potential contributing factors like GDP, education, crime rates, and more.

This visualization shows the association between GDP per capita and people’s freedom to make life choices. Each dot in the graph represents a country. It seems like that if a country’s logged GDP per capita is higher, then people in that country have more freedom to make their life choices. This makes sense because higher GDP per capita means people have more money, and if people are wealthier, then people can spend their money in whatever way they want. The top five countries with the highest GDP per capita are Luxemburg, Singapore, Ireland, Switzerland and the United Arab Emirates. The top five countries with the highest people’s freedom are Uzbekistan, Norway, Cambodia, Iceland, and Finland. The size of each dot is determined by the country’s median age. It is interesting to see that if GDP and people’s freedom is high, then the median age tends to be high as well.

This visualization shows the number of COVID-19 deaths in 2020 globally. Each dot represents the coordinates of a single country, so there is one dot per country. Smaller size and lighter shade dots represent countries that had smaller numbers of COVID-19 deaths in 2020. Larger size and darker shade dots represent countries that had greater numbers of COVID-19 deaths in 2020. It seems like the greatest number of COVID-19 deaths in 2020 occurred in European, North American, and South American countries.

We then plotted a visualization of COVID-19 Deaths against the index of institutional trust. In general, we can see the higher the index of trust, the lower number of COVID-19 deaths. This result shows that the people’s trust in their governments have an effect on COVID-19 deaths in their country.

This visualization plots each country’s ladder score against its COVID-19 deaths in the year of 2020. The ladder score is a measure of happiness, and is obtained by asking respondents to rate their current lives on a scale of 1 to 10. In this visualization, we can see that there is actually a positive correlation between COVID-19 related deaths and a country’s ladder score. This may be due to confounding variables that are not directly related to COVID-19. For instance, perhaps countries with higher death rates also tend to have certain economic or political structures that play a role in the higher ladder scores seen in the graph.

We hypothesized that perhaps COVID-19 deaths have a stronger negative effect on ladder score when we are past a threshold number of deaths. To pursue this, we divided the data into countries with less than 75 deaths per 100,000 people and those with more than 75 deaths per 100,000 people.

When only observing countries on the upper spectrum of COVID-19 deaths, there is a stronger negative correlation between COVID-19 deaths and ladder score. The countries with low COVID-19 deaths still have a positive correlation between deaths and ladder score. Although there could again be confounding variables, this suggests that COVID-19 may only start negatively impacting a country’s overall happiness when there are a significant amount of deaths. A cause of this could be that global media focuses on countries with high

Regression Modeling

We then created some regression models to predict the number of COVID-19 Deaths given the predictors. Based on our models, we can see that all of the predictors had a p-value of less than 0.05 which indicates they are strong predictors of COVID-19 Deaths. In our final model, we omitted the WHO Western Pacific Region variable as it is the only predictor that is not significant.

We also created some regression models to predict the Ladder Score of each country given the predictors. Based on our models, we can see that all of the predictors had a p-value of less than 0.05 which indicates they are strong predictors in predicting a country’s ladder score. In our final model, we omitted the Generosity variable as it is the only predictor that is not significant.

Conclusion

In general, we found out that COVID-19 deaths worldwide have negatively impacted a country’s ladder score — which perceives each country’s happiness. In addition, we also found out that a country’s median age has an effect on a country’s life expectancy score — which ultimately affects their country’s ladder score. Hence, it shows that the efforts made by governments, such as increased institutional trust and a high Gini coefficient of income, would help reduce COVID-19 deaths in their country. Thus, as a whole, COVID-19 has had a significant impact across the globe which drastically affects the happiness of the people of all the nations.