The INEQUALITREES Project aims at answering the following research questions about different dimensions of socio-economic inequalities
1. Levels and Individual Factors
1.1. What are the levels of inequality of opportunity and poverty in educational, income and health-related outcomes in the selected countries?
1.2. Which are the most predictive circumstances of individual outcomes in education, income and health?
1.3. Which intersections of particular circumstances characterize the most disadvantaged groups in the societies under study?
2. Spatial Distribution and Institutional Factors
2.1. What is the spatial distribution of inequality of opportunity and poverty in education, income and health within the selected countries?
2.2. Are the areas characterised by unequal opportunities also those with high poverty rates?
2.3. Which contextual and institutional characteristics affect the spatial distribution of socio-economic inequalities?
3. Machine Learning Methods
3.1. How can Machine Learning tools serve to integrate various data sources for the analysis of socio-economic inequalities?
3.2. To what extent do estimates from flexible Machine Learning techniques applied to large-scale integrated databases improve estimates from standard approaches applied to single datasets?
INEQUALITREES in a Nutshell
INEQUALITREES is an academic research project studying the levels, drivers, and spatial distribution of socio-economic inequalities in developed and developing countries with innovative methods and data sources.
The INEQUALITREES project investigates the levels and main drivers of two key manifestations of socio-economic inequality:
poverty and inequality of opportunity.
In line with the background of the researchers involved, the project is intrinsically interdisciplinary since we integrate theoretical and methodological contributions from economics, sociology, geography, anthropology and computer science.
We propose a cross-national view by focusing on Bolivia, Germany, India and Italy. The countries are selected based on the team’s extensive knowledge of national contexts as well as their privileged access to various interesting data sources. Furthermore, they are exemplary cases of societies that are characterized by different institutions, socio-economic structures and cultural values.
The project is multidimensional since we will analyse inequality of opportunity and poverty with respect to three key individual outcomes:
education, income and health.
Socio-economic inequalities are one of the big policy challenges at the global level. In this project, we draw on the concepts of inequality of opportunity and poverty as two widely accepted expressions of unfair inequality.
Poverty refers to a lack of sufficient socio-economic resources to make ends meet and to allow individuals to fully participate in social life.
Inequality of opportunity refers to the extent to which individual life outcomes are shaped by circumstances beyond individual control instead of individual effort and choices.
and Big Data
A key innovative feature of our project consists in the application of cutting-edge Machine Learning techniques. Machine Learning is a set of statistical techniques based on algorithms that learn from the data, and develop statistical models to make accurate out-of-sample predictions.
In our project, Machine Learning will be used for three main tasks:
1) Integrating data from different sources;
2) Extracting information from non-standard data sources (satellite images);
3) Estimating Inequality of opportunity and poverty measures across and within countries.