Thesis (Selection of subject)Thesis (Selection of subject)(version: 336)
Assignment details
   Login via CAS
Alternative approach to measuring development progress of countries.
Thesis title in Czech: Alternativní způsob měření rozvoje zemí.
Thesis title in English: Alternative approach to measuring development progress of countries.
Key words: Gross Domestic Product, Social Progress Index, K-means clustering, Bayesian Model Averaging
English key words: Gross Domestic Product, Social Progress Index, K-means clustering, Bayesian Model Averaging
Academic year of topic announcement: 2015/2016
Type of assignment: diploma thesis
Thesis language: angličtina
Department: Institute of Economic Studies (23-IES)
Supervisor: Mgr. Daniel Vach
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 22.09.2017
Date of assignment: 22.09.2017
Date and time of defence: 31.01.2018 08:30
Venue of defence: Opletalova - Opletalova 26, O206, Opletalova - místn. č. 206
Date of electronic submission:04.01.2018
Date of proceeded defence: 31.01.2018
Reviewers: PhDr. Lenka Šťastná, Ph.D.
 
 
 
URKUND check:
References
Human Development Report. Published for the United Nations Development Programme (UNDP). New York, 2014.

Hurvich, C.M., and Tsai, C.-L., 1989. Regression and time series model selection in small samples. Biometrika, Vol 76. pp. 297-307
Inclusive Wealth Report 2012. Measuring Progress toward Sustainability

Karl, A. and Lenkoski, A., 2012. Instrumental Variable Bayesian Model Averaging via Conditional Bayes Factors. working paper, arXiv:1202.5846v3 [stat.ME].

Schwarz, G., 1978. “Estimating the dimension of a model”. Annals of Statistics 6(2):461-464.
Preliminary scope of work
Motivation:
It is obvious that GDP is defective. It does not take into account the environment. It considers prisons and bombs as development but it has nothing in common with justice, happiness, fairness and community. Not surprisingly, that our world concentrating on how to produce more and more GDP, forgot that it is waving on the edge of ecological problems and overload with conflicts and anger.
A better approach should be considered to measure society, which would judge real things that matter to real population. Am I able to write and read? Do I have enough food? Do I have shelter? Am I safe? Can my society discriminate me? Is the future of my children protected? There no answers GDP could provide for all of those questions, because it simply cannot. Social Progress Index might be a better measure of the wellbeing of population and it does not depend on GDP. It is a new method by how we can look at the world.

Hypothesis:
1. Hypothesis #1: Countries with higher Social Progress Index do not need to have high GDP rate.
2. Hypothesis #2:Each of 3 dimensions of SPI consist of 4 different components.
3. Hypothesis #3: The best model for describing social progress depends on 12 components.

Methodology:
I will use K-means clustering analysis to make to group countries. This approach assumes a big variety of data models in order to identify the most likely number of clusters and the model using Bayes criteria and maximum likelihood estimation. The
optimal model is selected according to Bayesian’s information criterion.

Akaike’s information criterion is a measure of the goodness of fit of an estimated statistical model The AIC is an operational way of trading off the complexity of an estimated model against how well the model fits the data.

Bayesian Model averaging can provide a very big help in a field of economic growth, which developed a big number of competing theories. Fernandez, Ley and Steel in their work “Model uncertainty in cross-country growth regressions” (Fernandez, Ley and Steel (2001)) considered an extremely large set of possible models with 41 regressors. They had models to deal with.
The dataset of Social Price Index will be used. Instead of accentuating regular estimations of progress like income and investment, there are 50 indicators of ecological and social outcomes, which design a clearer picture of what life is truly like for ordinary people.
I will use 49 countries for investigation. All of the countries account for all continents, excluding Antarctica. There are 30 European countries, 3 African, 2 Oceanian countries, 3 South American, 3 North American and 8 Asian. This dataset present all types of countries – developed, developing and economies is transition

Outline:
1. Motivation: Economic growth alone is not sufficient for measuring social progress. A community, which neglects to meet basic human needs, to protect nature and environment, to provide opportunities to get basic knowledge, discriminate people and forget about existence of personal rights is not succeeding. Development and growth must involve not only economic progress but also must include social progress.
2. Studies on social progress: I will briefly describe determinants of social progress and will compare it to GDP.
3. Data:I will use data from social progress index for 49 different countries.
4. Methods: I will explain Bayesian model averaging,will include K-means clustering and BIC analysis.
5. Results: I will discuss my main results and findings
6. Concluding remarks: I will summarize my findings and their implications for policy and future research.
Preliminary scope of work in English
Motivation:
It is obvious that GDP is defective. It does not take into account the environment. It considers prisons and bombs as development but it has nothing in common with justice, happiness, fairness and community. Not surprisingly, that our world concentrating on how to produce more and more GDP, forgot that it is waving on the edge of ecological problems and overload with conflicts and anger.
A better approach should be considered to measure society, which would judge real things that matter to real population. Am I able to write and read? Do I have enough food? Do I have shelter? Am I safe? Can my society discriminate me? Is the future of my children protected? There no answers GDP could provide for all of those questions, because it simply cannot. Social Progress Index might be a better measure of the wellbeing of population and it does not depend on GDP. It is a new method by how we can look at the world.

Hypothesis:
1. Hypothesis #1: Countries with higher Social Progress Index do not need to have high GDP rate.
2. Hypothesis #2:Each of 3 dimensions of SPI consist of 4 different components.
3. Hypothesis #3: The best model for describing social progress depends on 12 components.

Methodology:
I will use K-means clustering analysis to make to group countries. This approach assumes a big variety of data models in order to identify the most likely number of clusters and the model using Bayes criteria and maximum likelihood estimation. The
optimal model is selected according to Bayesian’s information criterion.

Akaike’s information criterion is a measure of the goodness of fit of an estimated statistical model The AIC is an operational way of trading off the complexity of an estimated model against how well the model fits the data.

Bayesian Model averaging can provide a very big help in a field of economic growth, which developed a big number of competing theories. Fernandez, Ley and Steel in their work “Model uncertainty in cross-country growth regressions” (Fernandez, Ley and Steel (2001)) considered an extremely large set of possible models with 41 regressors. They had models to deal with.
The dataset of Social Price Index will be used. Instead of accentuating regular estimations of progress like income and investment, there are 50 indicators of ecological and social outcomes, which design a clearer picture of what life is truly like for ordinary people.
I will use 49 countries for investigation. All of the countries account for all continents, excluding Antarctica. There are 30 European countries, 3 African, 2 Oceanian countries, 3 South American, 3 North American and 8 Asian. This dataset present all types of countries – developed, developing and economies is transition

Outline:
1. Motivation: Economic growth alone is not sufficient for measuring social progress. A community, which neglects to meet basic human needs, to protect nature and environment, to provide opportunities to get basic knowledge, discriminate people and forget about existence of personal rights is not succeeding. Development and growth must involve not only economic progress but also must include social progress.
2. Studies on social progress: I will briefly describe determinants of social progress and will compare it to GDP.
3. Data:I will use data from social progress index for 49 different countries.
4. Methods: I will explain Bayesian model averaging,will include K-means clustering and BIC analysis.
5. Results: I will discuss my main results and findings
6. Concluding remarks: I will summarize my findings and their implications for policy and future research.
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html