Economics Report: Examining GDP and Life Satisfaction Relationship

This report investigates the statistical relationship between GDP per capita and average life satisfaction, utilizing data from the oecdbetterlifeindex website. Employing quantitative analysis techniques, specifically linear regression, the study aims to establish a cause-and-effect relationship, considering factors like linear relationship, normality, and homoscedasticity. The findings reveal a positive correlation between GDP and life satisfaction, particularly in poorer nations. The regression model indicates that life satisfaction increases with GDP per capita, although this effect diminishes as countries become wealthier. After removing outliers, the re-estimated model shows an improved fit, explaining a greater variance in life satisfaction. The report concludes with policy recommendations, emphasizing the importance of initiatives that boost productivity and suggesting further research into other variables influencing life satisfaction. Desklib provides access to similar solved assignments.

Economics 1
Economics and Quantitative Analysis
By
Name
Course
Instructor
Institution
Location
Date

Economics 2
Economics and Quantitative Analysis
Purpose
This report Gross domestic Product (GDP) is the monetary measure of a country’s
economic performance through estimation of aggregate output. Average life satisfaction on the
other hand, measures how individuals evaluate their life as a whole rather than their present
feelings. This research seeks to report on the statistical association between average life
satisfaction and GDP per Capita. The finding of this study will aid economists and policy makers
to understand the behavior of these economic variables.
Background
The relationship between GDP and average life satisfaction has attracted considerable
interest among scholars and economists alike. Proto and Rustichin (2014) found a positive
relationship between the two variables using cross sectional evidence. However, the scholars
proceeded to argue that there was no significant relationship between the variables using time
series analysis procedures. The researchers also concurred with Degutis, Urbonavicius, and
Gaizutis (2010) that there is a greater positive relationship between GDP and life satisfaction in
poorer nations compared to richer countries and regions. Economists are interested in this topic
because it is critical for policy making. Governments rely on economists to develop proper
measures of well-being and hence enabling governments to develop policies and initiatives that
cause a greater impact on the well-being of their citizens.
Method
The reliability of the data source is integral for any research. The data used for this study
was obtained from the oecdbetterlifeindex website. The website is a reliable secondary data
source for economists seeking to establish relationship between different economic aspects. This

Economics 3
study shall use the quantitative analysis techniques to establish the relationship between the
variables of interest. The linear regression model which is a predictive model shall be used to
establish relationship between gross domestic product and life satisfaction. The regression
analysis model is a scientific model that seeks to establish the cause and effect relationship
between variables. The model assumptions include presence of properties such as linear
relationship, normality, lack of autocorrelation, and homoscedasticity.
Results
Descriptive Analysis
Table 1
The table above shows the descriptive statistics of average life satisfaction scores and
annual GDP per capita. The mean life satisfaction score is 6.58 while mean per capital GDP for
the countries under study is $39011.51. Greece and Portugal recorded the minimum average life
satisfaction scores at 5.2. The highest average life satisfaction score was 7.5 which was attained
by Denmark, Finland, Iceland, Norway, and Switzerland. The minimum GDP per Capita was
Mexico’s $17,122.53 while the highest was Luxembourg’s $86,788.14.

Economics 4
Scatter Graph
Figure 1
Figure 1 above shows a scatter graph of average GDP Per capita and Average Satisfaction
scores. The scatter graph shows that as the average life satisfaction scores has a positive
correlation with average GDP per Capital up to some relevant level. As average GDP increased,
average life satisfaction increased up to some point where an increase in average GDP per capita
did not yield to an increase in average life satisfaction. This implies that the positive relationship
exists for poor countries but weakens as countries continue to become richer as measured by Per
Capita GDP.

Economics 5
Regression analysis
Figure 2
Figure 2 above is a regression model that can be used to predict average life satisfaction given
the GDP per capita. Average GDP per capita is the independent variable while average life
satisfaction is the dependent variable.
Regression equation and interpretation
The regression equation for this regression model is;
Y= 5.3652+0.000031433X
Where, Y represents Life satisfaction score
X represents average GDP Per capita.
The constant 5.36652 represents the Y-intercept which is the minimum life satisfaction score
realized in a country with $0 of average GDP Per capita. It is therefore the theoretical least
attainable life satisfaction score realized in a country with $0 of average GDP Per capita. It is
therefore the least attainable average life satisfaction score. The slope coefficient is
0.000031433. The gradient is a measure of change of average life satisfaction score for every

Economics 6
unit change in the average per capital GDP. Therefore, in this scenario, the mean increase in in
life satisfaction score for every unit $1 change in average per capita GDP is 0.000031433. For
instance, if per capital GDP is $10,000 dollars, the estimated average life satisfaction score is
obtained as Y=5.3652+0.000031433(10,000) = 5.67953.
Statistical Significance
There exists a statistically significant association between GDP per capita and average
life satisfaction. This is so because, the P-value of the variable (GDP per capita) is 0.000187192
which is less than 0.05 significance level. The statistical rule of the thumb is to reject the null
hypothesis that there exists no statistically significant relationship between the GDP per capita
and average life satisfaction when p-value is less than the level of significance of 0.05.
Good ness of fit
In the above model, R-squared measures the degree of variance in average life satisfaction score
that is explained by the model. The R-squared is 0.3489 which means that the model explains the
variation in life satisfaction by 34.89 percent. Therefore, we conclude that the model does not
provide a good fit.
Re-estimated regression model

Economics 7
Figure 3
Outliers are data points that differ significantly from other observations in the dataset.
Thus it is expected that when outliers are excluded from the dataset during regression analysis,
the resultant model will have a better goodness of it. Figure 3 shows the output of the regression
model when outlier data points (Luxembourg, Ireland, and Norway) are excluded. The gradient
coefficient increased from the earlier 0.000031433 to 0.0000551414 while the intercept declined
from 5.3652 from 4.5558. The R-squared of the new model has an R-squared of 0.4961 implying
that the new model explains the variation in the dependent variable by 49.61%. Therefore, the
removal of the outliers enhanced the goodness of fit of the regression model by 14.72%.
Discussion
The regression model is a reliable model in determining the association between
variations. The strengths of the model is that it has it is free from subjectivity of the analyst and
makes use of all data points unless where outliers exist, then the analyst uses scientific methods

Economics 8
to deal outliers. The method also maximizes the sum of squares of error terms and offers best
predictions of the dependent variable within the relevant range provided a linear relationship
exists. The findings of the study are consistent with the earlier studies conducted by Proto and
Rustichin (2014) that average life satisfaction scores and that there is a greater positive
relationship between GDP and life satisfaction in poorer nations compared to richer countries
and regions. The findings also have clear policy implications such that poorer countries should
prioritize initiatives that increase per capital GDP so as to increase average life satisfaction
scores. However, this does not mean that wealthy countries should reduce productivity.
Recommendations
i. This study recommends that all government policies should be geared towards initiatives
that increase productivity irrespective of whether they increase general life satisfaction or
not.
ii. The study also recommends that economists should seek more variables that affect
average life satisfaction since per capita GDP does not sufficiently explain the variation
in average life satisfaction.
iii. Finally, the research recommends that politicians should increase the agenda of their
manifesto during elections since electorates are not only satisfied by increased per capita
GDP but also other factors such as increased accessibility to quality health services and
improved security among other possible factors.

Economics 9
References
Degutis, M., Urbonavicius, S. and Gaizutis, A. (2010). Relation between Life Satisfaction and
Gdp in the European Union. Ekonomika, 89(1), pp.9-21.
Proto, E. and Rustichini, A. (2014). GDP and life satisfaction: New evidence | VOX, CEPR
Policy Portal. [Online] Voxeu.org. Available at: https://voxeu.org/article/gdp-and-life-
satisfaction-new-evidence [Accessed 25 May 2019].