Identification of possible determinants of Life Expectancy using Classification and Regression Tree (CART) analysis

Title

Identification of possible determinants of Life Expectancy using Classification and Regression Tree (CART) analysis

Research question

The aim of this study is to identify possible determinants of life expectancy (the dependent variable) between a number of predictor variables such as: gross domestic product, health expenditure, education expenditure, air pollution and access to clean water, sanitation and electricity.

Motivation

The motivation of this research ground in the importance of health in accelerating countries development.

 “Better health is central to human happiness and well-being. It also makes an important contribution to economic progress, as healthy populations live longer, are more productive, and save more.” (www.who.int/hdp/en/)

Life Expectancy at Birth is one of the most widely used summary measures of the population health status at system level.

Life Expectancy at Birth (LEB) is the average number of years a newborn infant would be expected to live if health and living conditions at the time of its birth remained the same throughout its life. It reflects the health of a country's people and the quality of care they receive when they are sick.

According to Wikipedia in the Bronze and Iron Age LEB was 26 years; the 2010 World LEB was 67.2, but Life Expectancy differs dramatically between countries, for example: in Swaziland LEB is about 49 years while in Japan is about 83 years.

Identify determinants of Life Expectancy using machine learning technique such as Classification and Regression Tree (CART) analysis can help focus interventions in country with low Life Expectancy.