GROUP ASSIGNMENT COVER SHEET

STUDENT DETAILS

Student name: Phạm Thảo Nguyên Student ID number: 31191025426

Student name: Nguyễn Minh Thư Student ID number: 31191024860 

UNIT AND TUTORIAL DETAILS

Unit name: Applied Econometrics Unit number: AE-DH45ISB-2

Tutorial/Lecture: Class day and time: Thursday – 8AM
Lecturer or Tutor name: Lê Trung Thành

ASSIGNMENT DETAILS

Title: Final Project

Length: 20 pages Due date: 29/4/2021 Date submitted: 21/4/2021

DECLARATION
I hold a copy of this assignment if the original is lost or damaged.

I hereby certify that no part of this assignment or product has been copied from any other student’s work or

from any other source except where due acknowledgement is made in the assignment.
I hereby certify that no part of this assignment or product has been submitted by me in another
 (previous or current) assessment, except where appropriately referenced, and with prior permission
from the Lecturer / Tutor / Unit Coordinator for this unit.
No part of the assignment/product has been written/ produced for me by any other person except

where collaboration has been authorised by the Lecturer / Tutor /Unit Coordinator concerned.
I am aware that this work may be reproduced and submitted to plagiarism detection software programs for
 the purpose of detecting possible plagiarism (which may retain a copy on its database for future
plagiarism checking).
Student’s signature: Phạm Thảo Nguyên
Student’s signature: Nguyễn Minh Thư
Note: An examiner or lecturer / tutor has the right to not mark this assignment if the above declaration has not
been signed.

1
Contents

I. Abstract..........................................................................................................................................3

II. Introduction...................................................................................................................................3

III. Theoretical Framework.................................................................................................................3

IV. Data Methodology..........................................................................................................................4

V. Descriptive Statistics (Code and Charts).....................................................................................6

1. GDP and Happy Planet Index scores...............................................................................................6

2. Life Expectancy and Happy Planet Index scores.............................................................................8

3. Wellbeing and Happy Planet Index scores.......................................................................................9

4. Ecological Footprint and Happy Planet Index Scores....................................................................10

5. Inequality and Happy Planet Index Scores.....................................................................................11

6. Correlation Matrix.........................................................................................................................12

VI. Result (model) and Discussion....................................................................................................13

VII. Appendix......................................................................................................................................16

VIII. References....................................................................................................................................20

2
I. Abstract

In this study, the Happy Planet Index (HPI) data of 140 nations in 2016 was used to calculate the effect of
The Gross Domestic Product (GDP) on HPI to figure out whether there is any relation between GDP and
HPI. The study also calculates the estimators of four variables, namely “average well-being, average life
expectancy, ecological footprint, inequality” in the HPI multiple regression model and analyze how these
variables relate to HPI scores. The result will be compared with previous study about ecological
footprints and inequality in well-being.

II. Literature review

1. The Happy Planet Index 2016 Report

The graph about Happy Life Years against Ecological Footprint shows that wealthy Western nations are
developed countries that have high standard of living, life expectancy and wellbeing scores (Appendix 1).
However, they have shown the tendency not to have high scores on HPI because of the pollution and
environment costs for drastic performance from factories to raise the economy. Although the United
States has a fairly high Happy Life Years score (The concept of ‘happy life years’ was originally
developed in the work of Ruut Veenhoven, described as ‘happy life expectancy), since the Ecological
Footprint is considered, the HPI score of the USA has been decreased. In contrast, various nations
achieved a higher Happy Life Years score with lower Ecological Footprint (Gursakal and Murat, 2018).
Costa Rica is the HPI top-ranking, not only in 2016 but also the third time this country became the HPI
score leader, and recorded a slightly higher Happy Life Years score with a significantly smaller
Ecological Footprint compared to the USA. This achievement can be reached because 99% of electricity
is produced by renewable sources and the government has made a commitment to go to carbon neutral by
2021 (Marshall, 2008).

2. Inequalities in well-being

During the past forty years, Western countries have increased the GDP and risen income inequality
(Quick, 2015). Study shows that an increase in GDP generally decrease inequalities in well-being, while
an increase in income inequality generally increases inequalities in wellbeing. Besides, there is a strong
evidence proving the higher income will lead to higher well-being at the individual level.

III. Introduction

Throughout past years, economists use The Gross Domestic Product (GDP) to measure the value of the
output of all goods and services produced within a country in a given year. Therefore, the economy of a
nation can be evaluated through this monetary measurement. This index has been used since 1955, after

3
the Bretton Woods conference. At that time, economists prefer using the Gross National Product (GNP)
to use GDP. However, in recent years, modern economists found out that GDP has some important
limitations, such as “the failure to represent the degree of income inequality in society” or “the failure to
indicate whether the nation’s rate of growth is sustainable or not” (Stiglitz, Fitoussi, & Durand, 2018). In
2006, Nic Marks, who founded the Centre for Well-being at the New Economic Foundation (NEF),
developed the Happy Planet Index (HPI). The index was an attempt to measure the nation’s economy in a
comprehensive view with human well-being and development, by calculate the well-being of all
individuals and how well countries are doing at achieving long, happy and sustainable lives.

IV. Theoretical Framework

The HPI was initially published in July 2006, the second edition was published in 2009 and the third was
in 2012. The score of HPI will be ranged between 0 and 100 and countries only archive high scores when
they reach all three goals included in the index: high expectancy, high satisfaction in life, and low
ecological footprint.

The HPI combines four elements that demonstrate the efficiency of using environmental resources to lead
long, happy lives for residents. It is calculated by the multiplication of well-being, life expectancy,
inequality of outcomes and divided by ecological footprint as the below formula:

Wellbeing × Life expectancy × Inequality of outcomes

HPI= According to the data of each variable
Ecological Footprint
will be illustrated as following (Marks, 2016):

 Wellbeing: How satisfied the residents of each country say they feel with life overall, on a scale
from zero to ten, based on data collected as part of the Gallup World Poll.
 Life expectancy: The average number of years a person is expected to live in each country based
on data collected by the United Nations.
 Inequality of outcomes: The inequalities between people within a country, in terms of how long
they live, and how happy they feel, based on the distribution in each country’s life expectancy
and wellbeing data. Inequality of outcomes is expressed as a percentage.
 Ecological Footprint: The average impact that each resident of a country places on the
environment, based on data prepared by the Global Footprint Network. Ecological Footprint is
expressed using a standardized unit: global hectares (gha) per person.

The index is a fundamental tool that helps the governments make judicious decisions and solve the
economic and social issues.

4
Besides, this study will analyze the estimators of four variables ( β 0 , β 1 , β 2 , β3 β 4) of the multiple
regression formula:

HPI=β 0 + β 1 Average Wellbeing + β 2 Average Life Expectancy + β 3 Footprint + β 4 Inequality + Error

V. Data Methodology
1. Download the 2016 data set from The Happy Planet Index website
(http://happyplanetindex.org/countries) to find the correlations between variables to figure out
which factor affects the Happy Planet Index the most in 2016. 
2. Load the necessary package for this analysis and import the data with read_xlsx() from readxl
package and I subset the columns that will be used in our data visualization and analysis. Then,
we rename the column names (or variables), to ease the analysis process.
3.
## # A tibble: 6 x 14
##   Rank  Country Region Avg.Life.Expect… Avg.Wellbeing Happy.Life.Years
##   <chr> <chr>   <chr>  <chr>            <chr>         <chr>           
## 1 110   Afghan… Middl… 59.667999999999… 3.8           12.396023808740…
## 2 13    Albania Post-… 77.346999999999… 5.5           34.414736010872…
## 3 30    Algeria Middl… 74.313000000000… 5.6           30.469461311230…
## 4 19    Argent… Ameri… 75.927000000000… 6.5           40.166673874579…
## 5 73    Armenia Post-… 74.445999999999… 4.3           24.018760060702…
## 6 105   Austra… Asia … 82.052000000000… 7.2           53.069497709526…
## # ... with 8 more variables: Footprint.gha <chr>, Inequality <chr>,
## #   Inequality.LE <chr>, Inequality.W <chr>, HPI <chr>, GDP <chr>,
## #   Population <chr>, GINI.Index <chr>

4. Correct the class of the variables, as we can see they appear to have chr as class.
## Observations: 140

## Variables: 14
## $ Rank                <int> 110, 13, 30, 19, 73, 105, 43, 8, 102, 87, ...
## $ Country             <chr> "Afghanistan", "Albania", "Algeria", "Arge...
## $ Region              <fct> Middle East and North Africa, Post-communi...
## $ Avg.Life.Expectancy <dbl> 59.668, 77.347, 74.313, 75.927, 74.446, 82...
## $ Avg.Wellbeing       <dbl> 3.800000, 5.500000, 5.600000, 6.500000, 4....
## $ Happy.Life.Years    <dbl> 12.396024, 34.414736, 30.469461, 40.166674...

5
## $ Footprint.gha       <dbl> 0.79000, 2.21000, 2.12000, 3.14000, 2.2300...
## $ Inequality          <dbl> 0.42655744, 0.16513372, 0.24486175, 0.1642...
## $ Inequality.LE       <dbl> 38.34882, 69.67116, 60.47454, 68.34958, 66...
## $ Inequality.W        <dbl> 3.390494, 5.097650, 5.196449, 6.034707, 3....
## $ HPI                 <dbl> 20.22535, 36.76687, 33.30054, 35.19024, 25...
## $ GDP                 <dbl> 690.8426, 4247.4854, 5583.6162, 14357.4116...
## $ Population          <dbl> 29726803, 2900489, 37439427, 42095224, 297...
## $ GINI.Index          <chr> "Data unavailable", "28.96", "Data unavail...

5. To see the statistics for this dataset, use summary().

##                           Region   Avg.Life.Expectancy Avg.Wellbeing  
##  Americas                    :25   Min.   :48.91       Min.   :2.867  
##  Asia Pacific                :21   1st Qu.:65.04       1st Qu.:4.575  
##  Europe                      :20   Median :73.50       Median :5.250  
##  Middle East and North Africa:14   Mean   :70.93       Mean   :5.408  
##  Post-communist              :26   3rd Qu.:77.02       3rd Qu.:6.225  
##  Sub Saharan Africa          :34   Max.   :83.57       Max.   :7.800  
##  Happy.Life.Years Footprint.gha      Inequality      Inequality.LE  
##  Min.   : 8.97    Min.   : 0.610   Min.   :0.04322   Min.   :27.32  
##  1st Qu.:18.69    1st Qu.: 1.425   1st Qu.:0.13353   1st Qu.:48.21  
##  Median :29.40    Median : 2.680   Median :0.21174   Median :63.41  
##  Mean   :30.25    Mean   : 3.258   Mean   :0.23291   Mean   :60.34  
##  3rd Qu.:39.71    3rd Qu.: 4.482   3rd Qu.:0.32932   3rd Qu.:72.57  
##  Max.   :59.32    Max.   :15.820   Max.   :0.50734   Max.   :81.26  
##   Inequality.W        HPI             GDP          
##  Min.   :2.421   Min.   :12.78   Min.   :   244.2  
##  1st Qu.:4.047   1st Qu.:21.21   1st Qu.:  1628.1  
##  Median :4.816   Median :26.29   Median :  5691.1  
##  Mean   :4.973   Mean   :26.41   Mean   : 13911.1  
##  3rd Qu.:5.704   3rd Qu.:31.54   3rd Qu.: 15159.1  
##  Max.   :7.625   Max.   :44.71   Max.   :105447.1

VI. Descriptive Statistics

1. GDP and Happy Planet Index scores

6
To test whether the GDP affects the Happy Planet Index score or not and how great is the affection. 

After log transformation, the relationship between GDP per capita and Happy Planet Index Score is more
clear. The Pearson correlation between these two variables is low as expected money cannot buy
happiness, at approximately 0.11. However, as it’s got a positive relationship, people who have more
money tend to have a little more happiness.

Pearson's product-moment correlation

data:  hpi$GDP and hpi$HPIt = 1.3507, df = 138, p-value = 0.179
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.05267424  0.27492060
sample estimates:
      cor 
0.1142272 

2. Life Expectancy and Happy Planet Index scores

7
Do the correlation test in order to interpret the relationship between Life Expectancy and Happy Planet
Index Scores.

Pearson's product-moment correlation

data:  hpi$Avg.Life.Expectancy and hpi$HPI
t = 7.5519, df = 138, p-value = 5.314e-12
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.4118020 0.6484859
sample estimates:
      cor 
0.5407609 

The relationship between Life Expectancy and Happy Planet Index is a weak positive one; however, we
can know that the more people live, the happier they are. According to what we can see from the plots,

8
until the age of 80, there is an increase in HPI scores; however, after the age of 80, the HPI scores seem to
reduce and meet a gradual decrease. This may state that even though there is a positive relationship
between Life Expectancy and Happy Planet Index, people find it hard to make themselves happy when
they grow old at a certain age (in this case, the age of 80 is the peak of growth)
3. Wellbeing and Happy Planet Index scores
Do the correlation test in order to interpret the relationship between Wellbeing and Happy Planet Index
Scores. We predicted that it would be a positive correlation.

Pearson's product-moment correlation

data:  hpi$Avg.Wellbeing and hpi$HPI
t = 6.9537, df = 138, p-value = 1.3e-10
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.3751905 0.6226690
sample estimates:
      cor 
0.5093868 

9
Wellbeing and Happy Planet Index also have a weak positive relationship, it’s about 0.51. We can know
that the better residents of each country say they feel with life overall, the happier they are. Nevertheless,
it is different from what we can see from the plots of Life Expectancy and Happy Planet Index, the
correlation between wellbeing and HPI Scores is a continuous upward trend, which means that there is no
such peak in the wellbeing that can make people feel less happy.
4. Ecological Footprint and Happy Planet Index Scores
Do the correlation test in order to interpret the relationship between Wellbeing and Happy Planet Index
Scores. We predicted that it would be a negative correlation.

Pearson's product-moment correlation

data:  hpi$Footprint.gha and hpi$HPI
t = -1.5565, df = 138, p-value = 0.1219
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.29091312  0.03532383
sample estimates:
       cor 
-0.1313492 

10
As predicted, the relationship between Ecological Footprint and Happy Planet Index Scores is negative -
around -0.131. The more people use productive surface areas; typically these areas are: cropland, grazing
land, fishing grounds, built-up land, forest area, and carbon demand on land, the more unhappy they feel.
However, people can still be happy in the first few numbers of Ecological Footprints, but then we can see
the total downward trend in the plots. The dots which represent the areas in the world only focus on the
first half of the graph, and the highest HPI scores we have is around 45, which accounts for about 3
(global hectares per person) of ecological footprints.
5. Inequality and Happy Planet Index Scores
We did the correlation test in order to interpret the relationship between Inequality and Happy Planet
Index Scores. We predicted that it would be a negative correlation.

Pearson's product-moment correlation

data:  hpi$Inequality and hpi$HPI
t = -6.2041, df = 138, p-value = 6.015e-09
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.5873938 -0.3263839
sample estimates:
   cor 
-0.467 

11
As it has a negative relationship between Inequality (%) and Happy Planet Index, it’s much higher than
that of ecological footprints. We know that the more inequalities people feel in terms of how long they
live, and how happy they feel, based on the distribution in each country's life expectancy and wellbeing
data, the more unhappy they feel. According to the plots, people who live in Sub Saharan Africa are
kindly aware of the inequalities happening around them, which leads to relatively low HPI Scores.
However, people in Americas and European countries, where they do not have great concern of
inequalities, have high HPI Scores. 
6. Correlation Matrix
After studying about the correlations of each factor that affect HPI Scores, we want to have a big picture
so we work on the correlation matrix between all of the factors.
a. Scale the data, an important step of meaningful clustering consists of transforming the
variables such that they have mean zero and standard deviation one.
##  Avg.Life.Expectancy Avg.Wellbeing     Happy.Life.Years  
##  Min.   :-2.5153     Min.   :-2.2128   Min.   :-1.60493  
##  1st Qu.:-0.6729     1st Qu.:-0.7252   1st Qu.:-0.87191  
##  Median : 0.2939     Median :-0.1374   Median :-0.06378  
##  Mean   : 0.0000     Mean   : 0.0000   Mean   : 0.00000  
##  3rd Qu.: 0.6968     3rd Qu.: 0.7116   3rd Qu.: 0.71388  
##  Max.   : 1.4449     Max.   : 2.0831   Max.   : 2.19247  
##  Footprint.gha       Inequality      Inequality.LE      Inequality.W    
##  Min.   :-1.1493   Min.   :-1.5692   Min.   :-2.2192   Min.   :-2.1491  
##  1st Qu.:-0.7955   1st Qu.:-0.8222   1st Qu.:-0.8152   1st Qu.:-0.7795  
##  Median :-0.2507   Median :-0.1751   Median : 0.2060   Median :-0.1317  
##  Mean   : 0.0000   Mean   : 0.0000   Mean   : 0.0000   Mean   : 0.0000  
##  3rd Qu.: 0.5317   3rd Qu.: 0.7976   3rd Qu.: 0.8221   3rd Qu.: 0.6162  
##  Max.   : 5.4532   Max.   : 2.2702   Max.   : 1.4059   Max.   : 2.2339  
##       HPI                GDP            Population     
##  Min.   :-1.86308   Min.   :-0.6921   Min.   :-0.2990  
##  1st Qu.:-0.71120   1st Qu.:-0.6220   1st Qu.:-0.2740  
##  Median :-0.01653   Median :-0.4163   Median :-0.2339  
##  Mean   : 0.00000   Mean   : 0.0000   Mean   : 0.0000  
##  3rd Qu.: 0.70106   3rd Qu.: 0.0632   3rd Qu.:-0.0913  
##  Max.   : 2.50110   Max.   : 4.6356   Max.   : 8.1562

a. Analyze the data into a table correlation matrix.

12
 Footprint.gha Inequality HPI
Avg.Life.Expectancy 0.62 -0.93 0.54
Avg.Wellbeing 0.67 -0.76 0.51
Footprint.gha 1.00 -0.72 -0.13
Inequality -0.72 1.00 -0.47
HPI -0.13 -0.47 1.00
Avg.Life.Expectancy Avg.Wellbeing
Avg.Life.Expectancy 1.00 0.68
Avg.Wellbeing 0.68 1.00
Footprint.gha 0.62 0.67
Inequality -0.93 -0.76
HPI 0.54 0.51
The correlation matrix will show an overall relationship between all of the variables we have; however,
we have already interpreted what we need to answer above.
VII. Result (model) and Discussion
To get the final model for our work, we will run the regression between one dependent variable (HPI
Scores) and 4 other independent variables (Life expectancy, Wellbeing, Ecological Footprint and
Inequalities)
Result:
Residuals:
  Min      1Q  Median      3Q     Max 
-3.8810 -1.4609 -0.7086  0.7723 16.3228 
Coefficients:
                         Estimate                   Std. Error         t value          Pr(>|t|)    
(Intercept)             -16.88989            6.43285           -2.626         0.00965 ** 
hpi$Avg.Wellbeing         4.56903      0.28523            16.019       < 2e-16 ***
hpi$Avg.Life.Expectancy   0.45882   0.06746            6.801         3.07e-10 ***
hpi$Footprint.gha        -3.45751        0.13486           -25.637        < 2e-16 ***
hpi$Inequality          -11.53511         5.77238             -1.998         0.04769 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 2.418 on 135 degrees of freedom
Multiple R-squared:  0.8939, Adjusted R-squared:  0.8908 
F-statistic: 284.4 on 4 and 135 DF,  p-value: < 2.2e-16

13
Final model:

HPI=− 16.89+4.57 Average Wellbeing+ 0.459 Average Life Expectancy − 3.46 Footprint . gℎa −11.545 Inequality

The p-values for all tested variables are less than our significance level which is 0.05, our sample data
provide enough evidence to reject the null hypothesis for the entire population. Our data favor the
hypothesis that there is a non-zero correlation. Changes in the independent variable are associated with
changes in the response at the population level. This variable is statistically significant and probably a
worthwhile addition to our regression model.

Compared to what have been studied, it is true that people in countries with high life expectancy, high
wellbeing, low ecological footprint and low inequality will tend to have higher HPI’s scores.((Marks,
2016). However, to be more specific, residents also feel unhappy when they are getting older at the
certain age (from the test is 80 years old) since Life Expectancy and HPI have a weak positive relation
and they have more satisfaction in life when life is an entireness. Besides, Ecological Footprint is a
fundamental concern that every government should pay more attention when the more serious pollutions
in air, water, soil, or impacts from greenhouse effect occur because Ecological Footprint and HPI have a
negative relation, the more pollutions in the environment, the less happy residents are. Inequality and
HPI has a negative relation same as Ecological and HPI, however, the scores of Inequality and HPI is
higher, which means in developing countries, such as nations in Sub Saharan Africa area, have low HPI
because there is a big gap between the rich and the poor, while in developed countries like in Europe or
America, there are higher HPI scores. The analysis found out the value of estimators of four variables (
β 0 , β 1 , β 2 , β3 β 4) , are -16.89; 4.57; 0.459, -3.46, and -11.54 respectively.

14
VIII. Appendix
Appendix 1

15
IX. References

1. Gursakal, S. and Murat, D., 2018. Statistically Positioning of Countries in the Context of Happy
Planet Index Data. Retrieved 19 April 2021, from https://dergipark.org.tr/en/download/article-
file/621679.

2. Marshall, C. (2008). BBC NEWS | World | Americas | Costa Rica bids to go carbon neutral.
Retrieved 26 April 2021, from http://news.bbc.co.uk/2/hi/americas/7508107.stm

3. Quick, A. (2015). Inequalities in Wellbeing | Challenges and opportunities for research and
policy. Retrieved 3 May 2021, from
https://b.3cdn.net/nefoundation/e99d6e3014fff0356e_lqm6i2tiw.pdf?
fbclid=IwAR3HtZ8Cf968VoPYYk3u2ql2RrpQf5b7aHKKeJ_tMqXK_pxzkCmjt69AHqQ

4. Stiglitz, J. E., Fitoussi, J., & Durand, M. (2018). Beyond GDP: Measuring what counts for
economic and social performance. Paris: OECD Publishing.

5. Marks, N., 2016. Happy Index 2016: Methods paper. Retrieved 19 April 2021, from
https://static1.squarespace.com/static/5735c421e321402778ee0ce9/t/578dec7837c58157b929b3d
6/1468918904805/Methods+paper_2016.pdf.

16