Professional Documents
Culture Documents
Part 1. Introduction
Energy has long been a crucial part of global economic growth (Liu and Hao 2018). During
the current period, our planet is experiencing significant transformation, ranging from the
industrial revolution, and technological advancement, to the agriculture 4.0 revolution, energy
still remains an indicator to determine national power and policy-making decisions (Chien
2022). However, economic amelioration relies mostly on energy sources from the natural
environment, possibly burnt or exposed in the near term. In that case, this would result in
deleterious damage to the long-term natural atmosphere sustainability (Tawalbeh et al. 2021).
Additionally, since most nations rely on energy for production, the demand for global energy
is growing (Sarkodie 2020). Therefore, national governments are investing efforts and money
in addressing the matter of energy depletion, which is the ratio of the value of energy
resources’ source involving coal, crude oil, and natural gas, to the lifetime of the remaining
reserves, in % of GNI (The World Bank n.d.; McBeath et al. 2022).
The creation of the Sustainable Development Goal of the UN in 2015 had an objective of
diversersed aspects: climate change and energy, human inequality, and poverty gaps (National
Geographic 2020). Acknowledging the essentials of energy in different parts of human life,
from education, transportation, and communication to production and medicine, the UN’s
sustainable development goals included one that sustainable, affordable, and modern energy
should be accessible to everyone in the global village in 2030 (UN 2022). Monitoring energy
depletion might help to enhance energy efficiency by understanding the risks and
opportunities and reducing the amount of energy usage and its waste (Wang et al. 2018; Raza
et al. 2018). Additionally, International Renewable Energy Agency (2023) proposed that an
appropriate method of dealing with energy depletion would further expand application in
renewable energy sources, which is a solid foundation for energy mix and develop creation
and technology for long-term energy solutions.
The relationship between energy consumption and GNI varies. Kahouli (2019) found out that
the relationship between energy consumption and GNI per capita in OECD countries was bi-
unidirectional, meaning both negative and positive relationships were detected. Similar
findings were confirmed in net oil importing countries and MINT countries (Mexico,
Indonesia, Nigeria, Turkey)-country groups can potentially gain accelerated growth rates (Lin
and Benjamin 2018; Kahia et al. 2017). Besides, AlKhars et al. (2020) also reported that the
relationship between energy depletion and GNI was inconclusive. LSE (2022) reported that
high-income countries, including the USA, the UK, European Union, which only account for
16% of the world population, are consuming an excessive 74% of worldwide energy.
Particularly, high-income countries like the US, Russia or Saudi Arabia are enjoying
prosperity by trading oil, gas, and coal, resulting in a depletion that could severely damage the
whole environmental condition (Abbasi et al. 2o22). In contrast, low-income countries - Latin
America and the Caribbean, Africa, the Middle East and Asia – only utilise8% of the globe’s
energy. Therefore, it is understandable that high-income countries might face a higher
possibility of high levels of energy depletion due to their over usage without proper control
and regulations.
Table of Contingency
LG MG HG Total
Low energy depletion (L) 8 10 7 25
High energy depletion (H) 2 4 4 10
Total 10 14 11 35
Table 2: Contingency Table of different country categories based on level of energy depletion
and level of GNI per capita
This research would determine whether the level of energy depletion and GNI per capita are
two statistically independent events by comparing P(H) to P(H|HG).
10
P(H) = =0.286
35
4
P(H ∨HG)= =0.36 ≠ 0.286 → P (H)≠ P(H∨HG )
11
Because P(H) differs from P(H|HG), energy depletion and GNI per capita do not satisfy the
qualifications of statistically independent events. In other words, these two events are
intercorrelated, or the possibility that a country possesses high energy depletion and GNI per
capita could affect each other’s occurrence (Dexter and Epstein 2018).
2
P(H|LG) = =0.2
10
4
P(H|MG) = = 0.286
14
From these calculations, we could conclude that P(H|LG) (0.2) < P(H|MG) (0.286) < P(H|HG)
(0.36), indicating that high-income countries have the most possibility of having high energy
depletion, and the countries in another two groups face a lower possibility. Low-income
countries and middle-income countries only have about 20% possibility to possess high
energy depletion.
Central of Tendency
LG MG HG
Mean 4.092 4.830 3.296
Median 1.357 3.003 0.301
Mode #N/A #N/A #N/A
Variation
LG MG HG
Range 24.272 19.977 10.574
Variance 55.391 32.852 15.639
Standard Deviation (SD) 7.443 5.732 3.955
Coefficient of Variation (CV) 181.893% 118.678% 119.982%
Q1 0.465 0.996 0.163
Q3 3.049 5.073 5.414
IQR 2.584 4.076 5.251
Lower -3.411 -5.118 -7.713
Upper 6.925 11.188 13.290
Table 3: Measurements of central of tendency and variance of energy depletion
Figure 1: The box-and-whisker-plot of energy depletion level in three nation’s groups.
Firstly, this research applies the formula detecting outliers: if a datapoint is lower than Q1 –
1.5 x IQR or higher than Q3 + 1.5 x IQR, the datapoint is an outlier, expressing an extremely
high or low datapoint compared to others. We detect that the low-income countries dataset has
one outlier, while the middle-income countries dataset has two outliers. Moreover, according
to the box-and-whisker plot in Figure 1, the outliers in this data set are large, which could
affect significantly when calculating the Mean. Because of the outliers, this research would
choose the Median as the measurement of central tendency instead of the Mean. While the
Mean is widely applied and can represent the whole data set since it examines all the data
points, it is affected by the outliers, especially the large ones. Therefore, under this
circumstance, the report would compare the Median of three nation groups. MG(3.003) >
LG(1.357) > HG(0.301), indicating that overall middle-income countries would have the
highest energy depletion (% GNI), while the high-income countries suffer quite low energy
depletion. However, as more than 5% would suggest a high level of energy depletion, the
central tendency indicates that the three groups in this research dataset do not pose an
extremely serious condition. Regarding the variance, IQR is selected because it considers only
the 50% middle data points as it is unaffected by the outliers. Since HG(5.252) > MG(4.046)
> LG(2.584) in IQR, data in high-income countries are more dispersed and varied; in contrast,
low-income countries’ data is more concentrated, not creating a big gap in half of the data.
According to the box-and-whisker plot, the length of the box is suggested by IQR, in which
the high-income countries are the lengthiest, and the shortest are low-income countries. Three
country groups experienced a right-skewed, meaning that data is more concentrated at a lower
rate. The whisker of middle and high-income countries are considerable and lengthier than the
low-income. Several countries have high energy depletion, ranging from more than 5% to
approximately 12%. Low-income countries have the shortest upper whisker, meaning most of
the data is not widely dispersed. However, low-income countries have an extremely large
outlier, a country gaining nearly 25% energy depletion.
b. Discussion
When constructing confidence intervals, it should be noted that the assumptions must be
satisfied. Because if these assumptions are not met, then the confidence interval may not be
valid and should not be used to make inferences about the population (Siegmund 1985).
The following presumptions should be taken into account while creating confidence intervals
(DiCiccio and Efron 1996):
Ensure the quantity being measured is normally distributed in the population.
Guaranteed randomness and representativeness of data. It is possible to use a random
sampling method, in which each member of the population has an equal chance of
being selected for the sample.
Make sure the sample data contains observations that are all independent of one
another. This implies that there are no connections between and no effect on one
another between the observations in a sample.
Verify that the sample size is large enough to support applying the central limit
theorem. Depending on the basic shape of the population distribution, this figure will
change, although it is often higher than 30.
b. Discussion
Suppose the number of countries in the dataset is reduced by half, then the possible impact on
the hypothesis testing results is:
First, regarding the statistical decision, it will remain unchanged. The explanation for this is
that when the number of countries is cut, the sample size will decrease, which will also reduce
the degree of freedom. Decreasing the degree of freedom causes the sample mean distribution
to approach a normal distribution, causing the sample mean to be closer to the population
mean (Taupin and Luzzati 1982). It will also make it more difficult for the test to reject the
null hypothesis since falling into the rejection zone will become more difficult (Rouder et al.
2009). Because we do not reject H0 in Part 4a, the statistical decision remains unchanged.
Second, consider the accuracy of the results. A decrease in sample size will increase the
standard error because there is an inverse relationship between them (). In other words, this
will increase the variability of the sampling distribution, the statistical power of the test will
decrease, and the accuracy will also decrease (Devlieger et al. 2016).
Third, in terms of possible errors committed, because we do not reject H0, the error
encountered will be identical to part 4a (type II error).
Part 5. Conclusions
The summary of findings in this report would be described clearly in this part.
Part II of the probability analysis shows that high-income countries are more likely to
experience high energy depletion. Part II of the Variation study similarly reveals that data in
high-income nations are more scattered and diversified, implying that data in this category
have a higher value to being highly diversified. This research shows a positive relationship
between GNI per capita and energy depletion, consistent with the Part 1 conclusions that
high-income nations are at high risk of energy depletion due to overuse and over-dependence
for trading and other economic activities.
However, the findings in Part II of the central analysis show that overall, middle-income
countries will suffer the most from energy depletion (as a percentage of GNI), while high-
income countries will suffer the least energy depletion. This demonstrates a different trend
than the previous conclusion. One probable factor is a lack of adequate control and regulation.
As mentioned in Part I, high-income nations with strong economies, industry, and
industrialization would consume a lot of energy and quickly deplete it. However, this number
can remain low if strict and tight control is maintained (Khan et al. 2016).
Recognizing the vital role of energy in the numerous areas discussed in Part I. This report has
calculated and concluded with our 95% confidence level that the intervals of the world
average energy depletion (in % of GNI) would lie between 2.186 and 6.088. While this range
is relatively safe when considering that higher than 5% poses hazard, the results of Section IV
hypothesis testing point to a likely future increasing trend in global average energy
depletion.Theses findings remind policymakers, environmentalists and national authorities of
necessitating action to mitigate the negative impacts on the socioeconomic system. In
particular, it is vital to monitor the state of energy depletion to provide suitable
recommendations for use and exploitation as soon as possible. The key paths that
governments must follow include expanding applications in renewable energy sources,
integrating the usage of multiple forms of energy, and creating methods for the exploitation of
long-term energy sources (Dincer 2000). Furthermore, each country must pay attention to the
Sustainable Development Goals, specifically Goal 7 of the UN, to achieve sustainable
economic development while maintaining a stable socio-environmental environment (UN
2022).
Biemer P.P (2010) ‘Total survey error: Design, implementation, and evaluation’, Public
opinion quarterly, 74(5):817-848.
Chien F (2022) ‘The mediating role of energy efficiency on the relationship between sharing
economy benefits and sustainable development goals (Case Of China)’, Journal of Innovation
& Knowledge, 7(4):100270.
Devlieger I, Mayer A and Rosseel Y (2016) 'Hypothesis testing using factor score regression:
A comparison of four methods', Educational and Psychological Measurement, 76(5):741-770,
doi:10.1177/0013164415607618.
Dexter F and Epstein R.H (2018) ‘Treating surgical turnover times as statistically independent
events when testing interventions and mobile applications’, Mhealth, 4.
Indeed (1 October 2022) ‘Pros and Cons of Stratified Sampling (With Definitions)’, Indeed,
accessed 2 May 2023. https://ca.indeed.com/career-advice/career-development/pros-and-cons-
of-stratified-sampling
International Renewable Energy Agency (2023) ‘World Energy Transitions Outlook 2022’,
IRENA website, accessed 2 May 2023. https://www.irena.org/Digital-Report/World-Energy-
Transitions-Outlook-2022
J. McBeath J, Berman M and Rosenberg J (2022) The political economy of oil in Alaska,
Lynne Rienner Publishers, doi:10.1515/9781685857820.
Kahia M, Aïssa M.S.B. and Lanouar C (2017) ‘Renewable and non-renewable energy use-
economic growth nexus: The case of MENA Net Oil Importing Countries’, Renewable and
Sustainable Energy Reviews, 71:127-140.
Kahouli B (2019) ‘Does static and dynamic relationship between economic growth and
energy consumption exist in OECD countries?’, Energy Reports, 5:104-116.
Karimi Askarani K, Stockwell EB, Piontek KR and Sale TC (2018) 'Thermal monitoring of
natural source zone depletion', Groundwater Monitoring & Remediation, 38(3):43-52,
doi:10.1111/gwmr.12286.
Khan SAR, Zaman K and Zhang Y (2016) 'The relationship between energy-resource
depletion, climate change, health resources and the environmental Kuznets curve: Evidence
from the panel of selected developed countries', Renewable and Sustainable Energy Reviews,
62:468-477.
Lin B and Benjamin I.N (2018) ‘Causal relationships between energy consumption, foreign
direct investment and economic growth for MINT: Evidence from panel dynamic ordinary
least square models’, Journal of Cleaner Production, 197:708-720.
Liu Y. and Hao Y. (2018) ‘The dynamic links between CO2 emissions, energy consumption
and economic development in the countries along “the Belt and Road”’, Science of the total
Environment, 645:674-683.
LSE (The London School of Economics and Political Science) (6 April 2022) ‘High-income
countries are responsible for 74 percent of excess resource use causing ecological
breakdown’, LSE website, accessed 2 May 2023. https://www.lse.ac.uk/News/Latest-news-
from-LSE/2022/d-Apr-22/High-income-countries-responsible-for-74-percent-of-excess-
resource-use
National Geographic (2020) ‘Sustainable Development Goals’, National Geographic,
accessed 3 May 2023. https://education.nationalgeographic.org/resource/sustainable-
development-goals
Raza S.A., Shah N. and Sharif A. (2019) ‘Time frequency relationship between energy
consumption, economic growth and environmental degradation in the United States: Evidence
from transportation sector’, Energy, 173:706-720.
Rouder JN, Speckman PL, Sun D, Morey RD and Iverson G (2009) 'Bayesian t tests for
accepting and rejecting the null hypothesis', Psychonomic bulletin & review, 16:225-237.
Sarkodie (2020) ‘Dynamic linkage between renewable and conventional energy use,
environmental quality, and economic growth: evidence from Emerging Market and
Developing Economies’, Energy Reports, 6:965-973.
Siegmund D (1985) Sequential analysis: tests and confidence intervals, Springer Science &
Business Media.
Tawalbeh M., Al-Othman A., Kafiah F., Abdelsalam E., Almomani F. and Alkasrawi M (2021)
‘Environmental impacts of solar photovoltaic systems: A critical review of recent progress
and future outlook’, Science of The Total Environment, 759:143528.
The World Bank (n.d.) ‘Metadata Glossary’, The World Bank, accessed 3 May 2023.
https://databank.worldbank.org/metadataglossary/world-development-indicators/series/
NY.ADJ.DRES.GN.ZS#:~:text=Energy%20depletion%20is%20the%20ratio,(capped%20at
%2025%20years)
UN (United Nations) (2022) ‘Ensure access to affordable, reliable, sustainable and modern
energy’, UN website, accessed 3 May 2023.
https://www.un.org/sustainabledevelopment/energy/
UN (United Nations) (2022) Ensure access to affordable, reliable, sustainable and modern
energy for all, UN website, accessed 4 May 2023. https://www.bing.com/search?
q=UN+SGS+7&cvid=cd6f7cf9428943c5a83b04ad7a139a4e&aqs=edge.