ABSTRACT The main goal of this report is to examine how the factors including life expectancy at birth, expected years of studying, mean years of studying and gross national income per c
Reasons for choosing this {ORIC -c- S5 S5 S4 k1 S*3 1H TH HH TH Hy 6
Economics plays a crucial role in shaping societal development and national progress, while econometrics applies statistical methods to economic data, providing empirical insights into economic relationships Although economic theories can be abstract and may not always align with reality, econometrics serves as a valuable tool for comparing theoretical predictions with actual data.
Econometrics has been a vital tool for economists to quantify economic relationships since its inception As students of economics, we understand the importance of studying Econometrics for effective logical reasoning and problem analysis.
Gross Domestic Product (GDP) has been the primary measure of a country's economic progress for over fifty years, originating in the late 1930s during the Great Depression to assess national welfare (Costanza, et al 2009) However, GDP is inadequate for evaluating true progress, as evidenced by recent financial crises, since it fails to reflect citizens' living standards, healthcare quality, or life expectancy Some nations exhibit high GDP yet low happiness levels, indicating that GDP measures economic performance rather than citizen well-being In response, the Human Development Index (HDI) was developed to prioritize people and their capabilities in assessing national development, highlighting that two countries with the same Gross National Income (GNI) can have vastly different human development outcomes Recognizing the significance of the HDI, our team aims to provide a comprehensive analysis of this index and its influencing factors, focusing on "Factors affecting Human Development Index in developing countries in the year 2020."
This article analyzes the Human Development Index (HDI) in 50 developing countries for the year 2020, exploring how various factors contribute to HDI variation Development is a multi-dimensional concept encompassing economic, social, political, legal, and security aspects Human development focuses on expanding choices for individuals, leading to better access to resources, higher living standards, and improved quality of life Key factors examined include life expectancy at birth (LE), expected years of schooling (EYS), mean years of schooling (MYS), and gross national income per capita (GNI) Following the analysis of these factors' impacts on HDI, the article will propose solutions to enhance HDI and promote economic sustainability in these nations.
3 Subject and scope of the research
This research examines the effects of life expectancy, expected years of schooling, mean years of schooling, and gross national income per capita on the Human Development Index (HDI) in developing countries By analyzing these key factors, the study aims to highlight their significance in shaping human development outcomes Understanding the interplay between these variables is crucial for policymakers seeking to enhance the quality of life and educational opportunities in these regions.
- Scope of the research: 50 developing nations in the year 2020
To analyze the impact of the four factors in the Human Development Index (HDI), our team employed the Ordinary Least Squares Method learned in class We utilized Stata software to execute the regression model and test our hypothesis The research report is structured into three primary sections.
Chapter 1: Literature review about Human Development Index and its components Chapter 2: Model Specification and Data Analysis
Chapter 3: Estimated model, hypothesis testing and statistical inferences
Our research report has some deficiencies and errors due to challenges in data collection and our limited experience with regression models We eagerly await feedback from PhD Vi Thi Phuong Mai to improve the quality of our report.
We also would like to send our gratitude to PhD Vi Thi Phuong Mai for her help throughout the Econometrics course.
Literature Review about Human Development Index and its components
Definition and Importance of HDI . 5-5 S< + ++s*+< +3 ke 9 IS.) on
The Human Development Index (HDD) is a statistical tool to estimate a country's overall accomplishment in its social and economic dimensions The three key dimensions are:
— A long and healthy life - measured by life expectancy
— Acquirement of education — measured by expected years of schooling
— A reasonable standard of living — measured by Gross National Income per capita
The Human Development Index (HDI) emphasizes individual potential for employment and quality of life It serves as a crucial metric for assessing a nation's ability to foster human development, complementing traditional economic indicators like GDP.
The Human Development Index (HDI) serves as a vital metric for assessing the socio-economic conditions of countries globally each year Nations are ranked based on various factors, with higher rankings signifying improved living standards, superior educational quality, and increased life expectancy Conversely, lower rankings reflect moderate education levels, living standards, and life expectancy, highlighting the urgent need for intervention in those regions.
The index serves as a tool to analyze the diverse policy options of countries For instance, when two nations exhibit similar gross national income (GNI) per capita, the Human Development Index (HDI) can effectively assess their human development outcomes.
Each year, the UNDP releases an annual report that ranks countries according to the Human Development Index (HDI) The HDI is a vital tool for assessing economic development, as it encompasses key social and economic indicators Overall, the HDI offers a more comprehensive and accurate reflection of human well-being compared to previous metrics.
In 1990, the United Nations Development Program (UNDP) transformed development theory and policy with its inaugural Human Development Report (HDR) and the introduction of the Human Development Index The HDR defined "human development" as the advancement of human well-being, providing country-level data on various well-being metrics This initiative expanded the tools for measurement and comparison available to governments, NGOs, and researchers, enhancing our collective understanding of development.
The Human Development Index (HDI) originated from the annual Human Development Reports by the United Nations Development Programme (UNDP), initiated by Pakistani economist Mahbub ul Haq His goal was to shift development economics from a focus on national income to people-centered policies, emphasizing that growth should be measured by human well-being The HDI is calculated using four key indicators: life expectancy for health, expected years of schooling, mean years of schooling for education, and Gross National Income per capita for standard of living.
Limitations of HDI
The Human Development Index (HDI), while an improvement over earlier metrics, continues to attract criticism from researchers Critics of the HDI argue that it falls short in fully capturing the complexities of human development, with their concerns typically falling into four main categories.
Critics argue that the Human Development Index (HDI) fails to fully capture the essence of human development Dasgupta and Weale (1992) highlight that the HDI is limited to socio-economic factors, neglecting important political and civil dimensions Ram (1992) further emphasizes that the index underestimates inequality among countries Additionally, Hicks (1997) points out that the HDI does not account for inequalities within countries or between genders.
Concerns regarding the Human Development Index (HDI) focus on data quality and the precise construction of the index Srinivasan (1994) critiques the HDI as conceptually weak and empirically flawed, highlighting issues such as incomplete coverage and measurement errors in gross national income for developing countries Additionally, the conversion to US dollars using purchasing power parity (PPP) has its own shortcomings Life expectancy data is unavailable for 87 out of 117 less developed countries, while under-five death statistics often rely on estimations rather than actual data collection Furthermore, literacy levels may be inaccurately represented due to the reliance on self-reported or indirectly inferred estimates.
The limitations of the Human Development Index (HDI) stem from aggregation issues, as highlighted by Desai (1991) He emphasizes the necessity for improved data and methodologies to accurately measure lifespan, assign appropriate weights to education levels, and assess living standards through GNP or income Enhancing both the weighting of components and the quality of data is essential for a more reliable HDI.
The last group of critics refers to the technical properties of the index (McGillivray, 1991; MacGillivray and White, 1993; Trabold-Nubler, 1991; Dossel and Gouner, 1994; Gormely, 1995; Noorbakhsh, 1998) McGillivray
According to (1991), the Human Development Index (HDI) offers limited insights, similar to existing development indicators, and does not effectively enhance understanding of inter-country development levels.
Other weaknesses of the HDI can be listed as follows:
Within countries, there is a lot of variation in HDI For example, North China is poorer than South-East
HDI indicates long-term changes, such as life expectancy and may not adapt to recent short-term changes
Increased national wealth does not necessarily lead to improved living conditions The Gross National Income (GNI) can enhance economic welfare only if allocated effectively For instance, a country that prioritizes military expenditure may see a rise in GNI, yet its overall well-being could decline.
A higher GNI per capita in a country can obscure significant inequality, as seen in nations like Russia and Saudi Arabia Despite their elevated real GNI per capita, these countries exhibit considerable disparities in wealth distribution In contrast, the Human Development Index (HDI) effectively highlights countries that may share similar GNI per capita yet differ in their levels of economic development.
Economic welfare is influenced by a number of other factors, including the risk of war, pollution levels, and access to safe drinking water
While the Human Development Index (HDI) represents an advancement over previous metrics, it remains an imperfect measure that fails to fully capture the essence of the Human Development concept.
The Human Development Index (HDI) is a composite measure that evaluates average achievements in three fundamental aspects of human development: a long and healthy life, knowledge, and a decent standard of living, as outlined in Human Development Reports Key indicators used to assess these dimensions include various health, education, and income metrics.
Health is often measured by life expectancy at birth (LE), which indicates the average number of years a newborn is expected to live, assuming current age-specific mortality rates remain constant The life expectancy index for a country at a specific age can be calculated using the formula: \$$\text{LE}_{x} = \frac{x - 20}{85 - 20} \times 100\$$ This metric provides valuable insights into the overall health and longevity of a population.
The life expectancy index includes two key components of education: expected years of schooling (EYS) and mean years of schooling (MYS) EYS represents the number of years a child of school entrance age can anticipate receiving based on current age-specific enrollment rates, while MYS reflects the average years of education attained by individuals aged 25 and older, derived from official education duration levels The education index (EI) is calculated using a specific formula.
The standard of living is defined by gross national income per capita (GNI), which represents the total income generated by an economy's production and ownership of production factors, minus the income paid to foreign owners of these factors This figure is adjusted to international dollars using purchasing power parity (PPP) rates and divided by the midyear population The income index (II) is calculated using the formula: II = 1 - ln(GNI per capita) - ln(100).
~ In(75000) — in(100) From the above equations, the dimension index (life expectancy index, education index, income index) is calculated by this general formula: actual value — minimum value
Dimension index = - — maximum value — minimum value
Having calculated the above indices, the HDI is calculated as the geometric mean (equally-weighted) of life expectancy, education, and income index, as follows:
The "Human Development Report" (HDR), first published by UNDP in 1990, emphasizes a human-centered approach to development This report has evolved over the years, introducing the Human Development Index (HDI) as a comprehensive measurement tool Since its inception, the HDI has been extensively researched and calculated, providing valuable insights into human development.
From 1990 to 2009, the UNDP published annual reports analyzing the Human Development Index (HDI), focusing on three key dimensions: health, education, and standard of living These reports utilized three primary indicators: life expectancy at birth, years of schooling, and gross national income per capita During this period, numerous researchers worldwide explored the factors influencing HDI, contributing to a deeper understanding of human development.
There have been many research papers relevant to the chosen topic that was discovered, showing many possible factors affecting the Human Development Index
In their 1993 research, "Human Development in Poor Countries: On the Role of Private Income and Public Services," Sudhir Anand and Martin Ravallion examined the impact of government spending on public services, including infrastructure, education, and healthcare, on human development across various nations They concluded that increased government investment in these areas positively influences human development Consequently, they recommended that developing countries allocate more resources to education and healthcare to improve overall human development levels.
Moreover, in the study "Troubling Tradeoffs in the Human Developing Index" by author Martin Ravallion, Development Research Group, Washington, USA given in
Model specification and Dafta analyS1S -S-Ă + se SSS+sssieeree 16 II 0i an
Method to gather đala 5 SH SH SH HH HH TH HH HH HH Hit 16 1.2 Method used to analyze đafa - Ác HS HH HH HH HH, 16 1.3 Method used to derive the model .- S5 S4 k + kSA HH, 16 2 Theoretical model SD€CIÍTCA[IOII SG SĂ SH HH kg key 17 PIN pvc on ae
In 2020, a quantitative analysis was conducted on secondary data from 50 observations representing 70 notable developing countries worldwide This data, essential for understanding the developing economy, was sourced from the United Nations Development Programme.
1.2 Method used to analyze data
Our group used Microsoft Excel to sort data and STATA software to process statistics and calculate the correlation matrix between the variables
1.3 Method used to derive the model
Based on previous studies, we can see a linear relationship between life expectancy at birth, expected years of schooling and gross national income per capita
As a result, we use a multiple regression model and the Ordinary Least Squares (OLS) method to create a linear function to test our hypotheses
The OLS method estimates the relationship by minimizing the total square error in the difference between the observed and predicted values of the dependent variables figured by a straight line
Least Squares Method i=1 ‘ , y-intercept Xi x (independent)
When using this method, we relied on basic assumptions of the OLS (Ordinary Least Squares) Consider the 2 variable regression model:
1 The regression model is linear in the parameters
2 X values are fixed in repeated sampling This also means X; and u; are uncorrelated
3 Zero mean value of disturbance u;(E(u,|X;)=0)
4 Homoscedasticity or equal variance of u;
5 No correlation between the disturbances (cov [u;u,|X;, X;] = E [ujuj|X;, X;] 0)
6 The model is correctly specified
7 The number of observations must be greater than the number of parameters to be estimated
8 The X values in a given sample must not all be the same
9 There is no perfect multicollinearity
Based on the theory discussed in the previous section, our group has built a model to investigate the effects of the indicators to the Human Development Index as follows:
HDI = f(LE, EYS, MYS, GNI) in which:
Variable Type of the variable | Meaning Unit
HDI Dependent variable Human Development Index
LE Independent variable | Life expectancy at birth Years EYS Independent variable | Expected years of schooling | Years MYS Independent variable | Mean years of schooling Years
Independent variable | Gross national income per | U.S dollars capita
To examine how these factors affect the Human Development Index (HDI), from the theory given, our group proposed the following regression models:
(PRE): InHDI, = 6) + ổ¡.InLE + 6;.InEYS + B3InMYS + B,InGNI + u; Sample regression model:
(SRE ): HDI; = By + B; -InLE + By InEYS + B3.InMYS + B,InGNI + @; in which:
Explanatory variable: LE, EYS, MYS, GNI £8: the intercept of the regression line
Bo: the estimate of the intercept of the regression line
Bi i=1,2,3,4: the slope of the regression line
Bini: 3,4: the estimate of the slope of the regression line u,: the error term of the regression line
@;: the estimate of the error term u;
The intercept of the regression line, denoted as \(B_0\), represents the expected value of InHDI when all explanatory variables are set to zero When controlling for other factors, a 1% increase in InLE results in an expected increase of \(B_1\%\) in InHDI Similarly, a 1% rise in InEYS leads to an expected increase of \(B_2\%\) in InHDI, while a 1% increase in InMYS corresponds to an expected increase of \(B_3\%\) in InHDI Lastly, a 1% increase in InGNI is associated with an expected increase of \(B_4\%\) in InHDI.
The complete definition of each variable is described thoroughly in Section 1 of the report
No | Variable | Meaning of the variable Expected sign of regression coefficient based on theories
1 InHDI The natural logarithm of Human
2 InLE The natural logarithm of Life] + expectancy
3 InEYS The natural logarithm of Expected] + years of studying
4 InMYS The natural logarithm of Mean years of | + studying
5 InGNI The natural logarithm of Gross national | + income per capita
The data for this article is sourced from the Human Development Report Office (HDRO) of the United Nations Development Programme (UNDP) website It comprises cross-sectional data with 50 observations from developing countries worldwide, collected in 2020 The dataset includes five key indicators: Human Development Index (HDI), Life Expectancy (LE), Expected Years of Schooling (EYS), Mean Years of Schooling (MYS), and Gross National Income per Capita (GNI).
Running the summarize command (sum InHDI InLE InEYS InMYS InGNI) in Stata, we yield the summary of each variable as follows:
Variable Obs Mean Std Dev Min Max
It can be therefore inferred from the summary statistics of the variables:
Human Development Index (HDI): InHDI has a mean value of -0.258178, the minimum value (-0.3523894) in Gabon and the maximum value (-0.1278334) in Poland with the standard deviation of 0616181
Life expectancy (LE): InLE has a mean value of 4.319156, the minimum value (4.197202) in Goban and the maximum value (4.38577) in Costa Rica with a standard deviation of 0.043454
The average expected years of schooling (EYS) across 50 observed countries is 2.652365 years, with Argentina having the highest EYS at 2.873565 years, while Lebanon records the lowest at 2.424803 years The standard deviation of EYS among these countries is 0.0993656.
The mean years of studying (MYS) across 50 observed nations is 2.254114, highlighting significant disparities in education levels Jamaica reports the highest MYS at 2.572612, while the Maldives has the lowest at 1.94591, with a standard deviation of 0.1607462 These figures underscore the concerning levels of literacy in certain countries.
The average gross national income per capita (GNI) among 50 countries is 9.677349, which is relatively low compared to Qatar's maximum value of 11.43408 In contrast, Samoa has the minimum GNI value of 8.749732, highlighting the increasing income disparity among nations Additionally, the high standard deviation of 0.5460636 further emphasizes this widening income gap.
Correlation is a statistical measure that indicates the degree to which two variables are linearly related, meaning they change together at a consistent rate As an effect size, the strength of the correlation can be described using the guidelines provided by Evans (1996) for the absolute value of r.
Correlation coefficient Strength of the correlation
Using the correlation command in Stata (corr INnHDI InLE InEYS InMYS InGND, the correlation matrix is yielded as follows:
1nHDI 1nLE 1nEYS 1nMYS 1nGNI
The analysis reveals a positive correlation of 0.5747 between Life Expectancy (InLE) and the Human Development Index (InHDI), confirming the anticipated relationship between these two variables This indicates that as the Human Development Index increases, life expectancy at birth also tends to rise.
+ InEYS and InHDI are positively correlated at a rate of 0.6329 The positive correlation coefficient indicates a positive relation between
Human Development Index and Expected years of schooling; this is in accordance with the initial expectation
InMYS and InHDI exhibit a positive correlation of 0.4369, confirming the anticipated relationship between the Human Development Index and mean years of schooling.
InGNI and InHDT exhibit a strong positive correlation of 0.8019, confirming the anticipated relationship between the Human Development Index and Gross National Income per capita.
- The correlation between independent variables:
+ + + + + + InLE and InEYS are positively correlated with a coefficient of 0.2025
The analysis reveals that InLE and InMYS exhibit a negative correlation with a coefficient of -0.1640 Conversely, InLE shows a positive correlation with InGNI, indicated by a coefficient of 0.4502 Additionally, InEYS is positively correlated with both InMYS and InGNI, with coefficients of 0.2503 and 0.2640, respectively Lastly, the correlation between InMYS and InGNI is also positive, albeit weak, with a coefficient of 0.0585.
Source of data nha
The data for this article is sourced from the Human Development Report Office (HDRO) of the United Nations Development Programme (UNDP) website It comprises cross-sectional data with 50 observations from developing countries worldwide, collected in 2020 The dataset includes five key indicators: Human Development Index (HDI), Life Expectancy (LE), Expected Years of Schooling (EYS), Mean Years of Schooling (MYS), and Gross National Income per Capita (GNI).
Running the summarize command (sum InHDI InLE InEYS InMYS InGNI) in Stata, we yield the summary of each variable as follows:
Variable Obs Mean Std Dev Min Max
It can be therefore inferred from the summary statistics of the variables:
Human Development Index (HDI): InHDI has a mean value of -0.258178, the minimum value (-0.3523894) in Gabon and the maximum value (-0.1278334) in Poland with the standard deviation of 0616181
Life expectancy (LE): InLE has a mean value of 4.319156, the minimum value (4.197202) in Goban and the maximum value (4.38577) in Costa Rica with a standard deviation of 0.043454
The average expected years of schooling (EYS) across 50 observed countries is 2.652365 years, with Argentina having the highest EYS at 2.873565 years, while Lebanon records the lowest at 2.424803 years The standard deviation of EYS among these countries is 0.0993656.
The mean years of studying (MYS) across 50 observed nations is 2.254114, highlighting significant disparities in education Jamaica reports the highest MYS at 2.572612, while the Maldives has the lowest at 1.94591, with a standard deviation of 0.1607462 These figures underscore the concerning levels of literacy in certain countries.
The average gross national income per capita (GNI) among 50 countries is 9.677349, which is notably lower than Qatar's maximum value of 11.43408 In contrast, Samoa has the minimum GNI value of 8.749732, highlighting the increasing income disparity among nations Additionally, the high standard deviation of 0.5460636 further emphasizes this income inequality.
Correlation is a statistical measure that indicates the degree to which two variables are linearly related, meaning they change together at a consistent rate As an effect size, the strength of the correlation can be described using the guidelines provided by Evans (1996) for the absolute value of r.
Correlation coefficient Strength of the correlation
Using the correlation command in Stata (corr INnHDI InLE InEYS InMYS InGND, the correlation matrix is yielded as follows:
1nHDI 1nLE 1nEYS 1nMYS 1nGNI
The analysis reveals a positive correlation of 0.5747 between Life Expectancy at Birth (InLE) and the Human Development Index (InHDI), confirming the anticipated relationship between these two variables.
+ InEYS and InHDI are positively correlated at a rate of 0.6329 The positive correlation coefficient indicates a positive relation between
Human Development Index and Expected years of schooling; this is in accordance with the initial expectation
InMYS and InHDI exhibit a positive correlation of 0.4369, confirming the anticipated relationship between the Human Development Index and mean years of schooling.
InGNI and InHDT exhibit a strong positive correlation of 0.8019, confirming the anticipated relationship between the Human Development Index and Gross National Income per capita.
- The correlation between independent variables:
+ + + + + + InLE and InEYS are positively correlated with a coefficient of 0.2025
The analysis reveals a negative correlation between InLE and InMYS, with a coefficient of -0.1640 Conversely, InLE shows a positive correlation with InGNI, indicated by a coefficient of 0.4502 Additionally, InEYS is positively correlated with both InMYS and InGNI, with coefficients of 0.2503 and 0.2640, respectively Lastly, the correlation between InMYS and InGNI is also positive, albeit weaker, with a coefficient of 0.0585.
DesCrIpfive SÍA(ISÍICS Q2Ặ LH HH HH HH HH HH HH TH Hit 20 3.3 Correlation matrix between variables - sex kg 21
Using the data obtained and the Stata software to yield the result of the Ordinary Least Squares (OLS) Estimation Method as follows:
Source ss at MS Number of obs = 50
Adj R-squared = 0.9968 Total „186042459 49 003796785 Root MSE = „00346
1nRHDI Coef Std Err t P>ịtl (95% Conf Interval]
1nLE - 458207 „0132002 34.71 0.000 - 4316204 - 4847936 1nEYS „2039762 - 0053834 37.89 0.000 „1931336 - 2148189 1nMYS - 1439667 „0032756 43.95 0.000 „1373694 „1505641 1nGNI -0617916 „0010388 59.48 0.000 „0596993 „0638839 _cons -3 700761 „0543132 -68.14 0.000 -3.810154 -3.591369
The coefficient of determination reveals that 99.71% of the variation in the dependent variable, InHDI, is explained by life expectancy (InLE), expected years of schooling (InEYS), mean years of schooling (InMYS), and gross national income per capita (InGND).
Using the result generated by Stata, we can conduct our estimated model as follows: InHDI; = -3.700761 + 0.458207.InLE + 0.2039762InEYS + 0.1439667InMYS
Given the hypothesis: nụ The model does not omit influential variables H1: The model omits influential variables Running the Ramsey RESET test in Stata, yield the following result:
Estimated models, hypothesis testing and statistical inferences
Testing
Given the hypothesis: nụ The model does not omit influential variables H1: The model omits influential variables Running the Ramsey RESET test in Stata, yield the following result:
Ramsey RESET test using powers of the fitted values of 1nHDI
Ho: model has no omitted variables
P-value = 0.0186 > ô =0.01 — do not reject Ho
In conclusion, the model does not omit influential variables at a significance level of 1% but omits influential variables at the significance levels 5% and 10%
Multicollinearity arises when independent variables exhibit a strong linear correlation, leading to inaccurate estimates To identify this issue, one can analyze the correlation coefficient matrix or utilize the variance inflation factor (VIF) in Stata The first method involves examining the correlation matrix.
| 1nHDI 1nLE 1nEYS 1nMYS 1nGNI
The correlation matrix indicates that the correlation coefficients among the explanatory variables are below 0.8, suggesting that there is no very strong correlation between any two variables.
Therefore, the possibility of multicollinearity is low e Second method: Considering variance inflation factor (VIF) in Stata
Given the hypothesis: fi The model does not have multicollinearity H1: The model has multicollinearity Running the variance inflation factor (VIF) in Stata, yield the following result:
We can see that all the yielded VIF values are smaller than L0 — not reject Ho — reject multicollinearity
In conclusion, multicollinearity does not happen in the model
Using Imtest, White heteroskedasticity test: fi The model doesn’t have heteroskedasticity H1: The model has heteroskedasticity Using the white test command in Stata, yields:
+ quiet reg lnHDI lnLE lnEYS lnMYS lnGNI
White's test for Ho: homoskedasticity against Ha: unrestricted heteroskedasticity chi2 (14) 47.39
Cameron & Trivedi's decomposition of IM-test
With significance level ô = 0.01,0.05 and 0.1, we have P-value = 0.000 < ô => reject
Therefore, the model has heteroskedasticity
Remedy for heteroskedasticity: Using weighted least square regression to limit the effect of heteroskedasticity
Running the command wils0 InHDI InLE InEYS InMYS InGNI, wvar(InHDI InLE InEYS InMYS InGNI) type(abse), yields:
- wlsO InHDI lnLE lnEYS lnMYS lnGNI, wvar(1nHDI lnLE lnEYS lnMYS 1nGNI) type (abse) WLS regression - type: proportional to abs(e)
Source 55 df MS Number of obs = 50
Adj R-squared = 0.9995 Total „035313321 49 „00072068 Root MSE = -00059
1nHDI Coef Std Err t P>lt| [95% Conf Interval]
1nLE 463265 007847 59.04 0.000 4474603 4790697 Ả1nEYS 1928796 -0028228 68.33 0.000 1871942 198565 1nMYS „1409969 „001387 101.66 0.000 1382033 1437904 1nGNI „0639651 0006992 91.48 0.000 0625568 0653735 _cons =3 706001 0294824 -125.70 0.000 =3 765381 -3.64662
The cross-sectional nature of the data eliminates the necessity for autocorrelation testing, which measures the similarity between a time series and its lagged version across successive intervals.
In summary, the analyzed model exhibits heteroskedasticity and lacks normal distribution, issues that can be addressed by applying the Weighted Least Squares (WLS) method and expanding the sample size The testing results lead to the formulation of the following sample regression function.
The coefficient of determination R2 = 99.96% indicates that the independent variables can explain 99.96% of the variation in the dependent variable (InHDI)
3.1 Testing the consistency of the regression result with the theories
The analysis of the model indicates that independent variables significantly influence the human development index (HDI), aligning with the theoretical framework established in Chapter I and the anticipated variables discussed in Chapter II Notably, there is a positive correlation between life expectancy and HDI; a 1% increase in life expectancy results in a 0.463265% increase in HDI, highlighting the critical role of physical capacity, particularly in medical and healthcare sectors, in enhancing human development.
There is a positive correlation between expected years of schooling (EYS) for children under 18 and the Human Development Index (HDI), with a 1% increase in EYS leading to a 0.1929% rise in HDI This indicates that investing in education for the next generation significantly enhances human development within a country Similarly, mean years of schooling (MYS) for individuals over 25 also positively impacts HDI, as a 1% increase in MYS results in a 0.1410% increase in HDI Higher educational attainment contributes to improved individual capabilities and overall societal progress.
Gross national income per capita with HDI have a positive relationship (when GNI increases by 1%, HDI will increase by 0.0639651%) Human development is partly reflected through their financial capacity
Comment: These results are consistent with the theories and studies above
3.2 Testing individual regression coefficients with significant level ô= 0.05 fre =0
B, has the test statistic t = 34.71 and the corresponding P-value = 0.000 < ô= 0.05
—>Reject Hạ> At 95% confidence interval, life expectancy has a significant effect on HDI growth > Consistent with the economic theory
B, has the test statistic t = 37.89 and the corresponding P-value = 0.000 < ô= 0.05 with significant level ô= 0.05
—>Reject Hạ > At 95% confidence interval, expected years of schooling has a significant effect on HDI growth > Consistent with the economic theory
Bs has the test statistic t = 43.95 and the corresponding P-value = 0.000 < ô= 0.05 with significant level ô= 0.05
Reject H, > At 95% confidence interval, expected years of studying has a significant effect on HDI growth > Consistent with the economic theory
B, has the test statistic t = 59.48 and the corresponding P-value = 0.000 < ô= 0.05 with significant level ô= 0.05
—>Reject Hạ > At95% confidence interval, GNI has a significant effect on HDI growth
> Consistent with the economic theory
3.3 Testing the overall significance of the model fir R; =0 H: Ro >0
According to the estimation output, test statistics: F, = 3876.52 and the corresponding P-value = 0.000 < 0.05 (5% significant level)
> All the independent variables (life expectancy, expected years of schooling, mean years of schooling, GND) jointly explain for the variation in the value of HDI growth
4 Explanation of the yielded result
The yielded sample regression function implies that there is a positive relationship between independent and dependent variables in the model This can be due to the following reasons:
There is a strong correlation between life expectancy at birth and the Human Development Index (HDI), as longer life spans often indicate better physical health and greater access to healthcare services This increased longevity provides individuals with enhanced opportunities for both physical and mental development.
There is a significant positive correlation between expected years of schooling and the Human Development Index (HDI) Expected years of schooling represent the anticipated duration a 2-year-old child will spend in education Increased investment in education reflects a commitment to nurturing a nation's future leaders Education plays a crucial role in a child's overall development and fosters positive behavior A nation's prosperity hinges on its focus on youth, as they are vital for economic sustainability and societal progress.
There is a positive correlation between mean years of schooling and the Human Development Index (HDI) Mean years of schooling refers to the average number of completed education years for individuals aged 25 and older, excluding repeated grades Increased educational attainment enhances knowledge and practical skills, extending beyond classroom activities Consequently, individuals are better prepared for the job market and develop a more advanced intellect.
There is a positive correlation between per capita income and Human Development Index (HDI), as higher income levels enable individuals to invest more in essential areas such as healthcare, education, and overall quality of life This financial capacity fosters a higher standard of living and enhances opportunities for comprehensive development, making financial resources a crucial element in promoting human development.
5 Some measures to improve HDI
Despite being a single indicator, HDI still acts as a complete tool to assess the social and economic development of countries around the world In order to increase HDI,
29 several measures relating to improving life expectancy, education and per capita income are essential
Measures to increase life expectancy:
Improving the minimum standard of living so that everyone can have access to basic needs such as shelter and food, clean water, etc
Investing in advanced nursing facilities and providing support through call lines and online services
Detecting acute infectious diseases, ensuring the reporting of infectious diseases, limiting disease transmission, and adopting control measures during infectious disease outbreaks to avoid diseases caused by infectious agents
To promote longer life spans, it is essential to keep citizens well-informed about health management and beneficial habits Governments and authorities can play a crucial role by organizing health programs and regulating the consumption of unhealthy foods.
Measures to increase the education level:
Lowering education costs enhances accessibility, motivating students to pursue their studies Educational institutions can seek funding from organizations to provide scholarships and financial aid for underprivileged students Additionally, fostering a love for learning in young learners requires parents and guardians to prioritize their children's education.
Providing parents with information on the value of education will be crucial to increasing and maintaining school enrollment
The authority should also pay attention to the local’s education system closely, by encouraging the elite of the society financially or mentally
The curriculum must be inclusive and suitable for all learners Educators should focus their teaching methods and adapt their styles based on students' understanding of the material presented in class.
To enhance educational quality, it is essential for policymakers to prioritize increased funding for both new school construction and the renovation of existing facilities Additionally, raising teachers' salaries is crucial, as many educators are drawn to positions in wealthier districts.
To enhance teaching quality in underfunded schools, it is crucial for policymakers and school officials to collaborate in attracting and retaining educators This initiative can significantly benefit students with higher educational needs by providing them with improved teaching conditions Additionally, implementing measures to increase gross national income per capita can further support these efforts.
The model effectively illustrates the variation of the Human Development Index (HDI) based on the variables Life Expectancy (LE), Expected Years of Schooling (EYS), Mean Years of Schooling (MYS), and Gross National Income (GNI) All parameters are statistically significant, aligning with the assumptions of the classical linear model without any defects Notably, each independent variable significantly impacts the dependent variable at a 0.5% significance level, and the model boasts a coefficient of determination (R²) of 99.96%, indicating that these variables account for 99.96% of the variation in the dependent variable (InHDD).
The research conducted by our group, utilizing data from the United Nations Development Programme (UNDP), identifies key factors influencing the Human Development Index (HDI) across 50 developing countries Our analysis reveals that life expectancy, expected years of schooling, mean years of schooling, and Gross National Income (GNI) per capita significantly contribute to improving HDI, aligning with established theoretical models.
Analyzing the Human Development Index (HDI) provides valuable insights into a country's progress By examining the HDI of various developing nations, we can understand the factors influencing their development This awareness enables countries to recognize their challenges and formulate targeted strategies for human development As individuals are the most significant asset of any nation, enhancing human development directly contributes to national prosperity and strength Ultimately, the advancement of people equates to the advancement of the country.
The Human Development Index (HDI) is a composite measure that evaluates a country's average achievements in three key dimensions of human development: health, education, and standard of living It emphasizes that human capabilities should be the primary criteria for assessing development, rather than solely economic growth The HDI is calculated using life expectancy at birth for health, mean years of schooling and expected years of schooling for education, and gross national income per capita for standard of living While the HDI provides valuable insights, it does not account for inequalities, poverty, or empowerment, necessitating the use of additional indicators for a comprehensive understanding of human development.
Human Development Index: Methodology and Measurement https://ora.ox.ac.uk/objects/uuid:98d15918-dca9-4df1-8653-
60df6d0289dd/download _file?file format=application/pdf&safe_filename=HDI_ meth odology.pdf&type_of_work=Report
The Human Development Index - The History https://scholarworks.umass.edu/cgi/viewcontent.cgi?article01 &context=peri_work ingpapers
Human Development Index (HDD - A poor representation to Human Development Approach https://www.researchgate.net/profile/Izete-Bagolin-
2/publication/228427587_Human Development _Index_HDI-
A_poor_representation_to Human Development_Approach/links/Odeec53c8f9477f8d a000000/Human-Development-Index-HDI-A-poor-representation-to- Human- Development-Approach.pdf
The Human Development Index — a better indicator for success? https://www.sustainablegoals.org.uk/human-development-index-better-indicator- success/
Methodological datasheet: Human Development Index https://en.eustat.eus/document/datos/PL metod/IDH_IDH_i.html
Human Development in Poor Countries: On the Role of Private Incomes and Public Services https://www.aeaweb.org/articles?id.1257/jep.7.1.133
Troubling Tradeoffs in the Human Developing Index
33 https://elibrary.worldbank.org/doi/pdf/10.1596/1813-9450-5484
Magazine: Biohealth - Correlation Between Human Development Index and Infant Mortality Rate Worldwide https://biotech-health.com/correlation-between-human-development-index-and-infant- mortality-rate-worldwide/
Analysis indicator of factors affecting Human Development Index (IPM) https://www.researchgate.net/publication/324946627_ ANALYSIS INDICATOR OF FACTORS AFFECTING HUMAN DEVELOPMENT INDEX IPM
APPENDIX The data set: Human Development Index and its components in 50 developing countries in the year 2020
Country Human Life Expected | Mean years | Gross
Development | Expectancy | years of| of national Index (HDI) | at birth (LE) | schooling | schooling | income per
Stata regression and estimation output
*Summary of the variables in the regression model* sum 1nHDI 1nLE 1nEYS 1nMYS 1nGNI
Variable | Obs Mean Std Dev Min Max
1nHDI | 50 -.258178 -0616181 -.3523984 -.1278334 inLE | 50 4.319156 -043454 4.197202 4.38577 1nEYS | 50 2.652365 „0993656 2.424803 2.873565 1nMYS | 50 2.254114 - 1607462 1.94591 2.572612 inGNI | 50 9.677349 - 5460636 8.749732 11.43408
*Running a correlation matrix between variables* corr 1nHDI 1nLE 1nEYS 1nMYS 1nGNI
I 1nHDI 1nLE 1nEYS 1nMYS 1nGNI
*Running a regression model* reg 1nHDI 1nLE 1nEYS 1nMYS 1nGNI
Source | ss at MS Number of obs = 50
1nHDI | Coef Std Err t P>ịtl [95% Conf Interval] inLE | „458207 „0132002 34.71 0.000 „4316204 - 4847936 1nEYS | „2039762 „0053834 37.89 0.000 „1931336 2148189 1nMYS | „1439667 „0032756 43.95 0.000 „1373694 „1505641 1nGNI | „0617916 „0010388 59.48 0.000 „0596993 „0638839