Dependence Analysis Between Childhood Social Indicators and Human Development Index Through Canonical Correlation Analysis

Raquel Lourenço Carvalhal Monteiro (), Valdecy Pereira () and Helder Costa ()
Additional contact information
Raquel Lourenço Carvalhal Monteiro: Universidade Federal Fluminense
Valdecy Pereira: Universidade Federal Fluminense

Child Indicators Research, 2020, vol. 13, issue 1, No 19, 337-362

Abstract: Abstract This paper presents a dependence analysis between childhood social indicators (selected from the UNICEF and World Development Indicators) and the Human Development Index (HDI). This analysis, made through a canonical correlation, aimed to measure the relationship between child well-being and the modern standards of sustainable social development. First we have selected variables related to basic needs for children until primary school from the UNICEF database, and to mitigate missing values problem, for each country we have taken the average value per year, and, if missing values problem persists, a proper statistical imputation technique was applied. Then, with all variables having complete cases, the canonical correlation analysis generated a canonical space divided into four quadrants in order to verify the relations between variables and countries. We have found two significant characteristic roots with canonical correlation values of 0.91 and 0.56, each characteristic root was, respectively, labeled as “Health & Primary Schooling” (showing an inverse correlation between neonatal mortality rate and health and primary schooling) and “Primary Education” showing a positive correlation between primary education enrollments and primary education completion. Our approach indicates that the selected child well-being indicators not only are correlated to the HDI, but they also complement this development measure considering child well-being indicators, because considering the health and education variables it could be identified countries from a superior HDI class that are more similar with countries from an inferior HDI class and countries from an inferior HDI class that are more similar with countries from a superior class. Although the selected variables represent the underlying conditions for a child to grow up with dignity, according to United Nations’ Sustainable Development Goals, the data availability for variables with low occurrences of missing cases was scarce, preventing the use of all available variables from the UNICEF database. We have divided the canonical space into four quadrants, each one with dominant characteristics from a specific HDI class. Then, the presented 182 countries were plotted against this space in order to relate the childhood well-being indicator with the HDI classes.

Keywords: Child well-being; Human development index; Canonical correlation (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12187-019-09715-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:chinre:v:13:y:2020:i:1:d:10.1007_s12187-019-09715-6

Ordering information: This journal article can be ordered from
http://www.springer. ... f-life/journal/12187

DOI: 10.1007/s12187-019-09715-6

Access Statistics for this article

Child Indicators Research is currently edited by Asher Ben-Arieh

More articles in Child Indicators Research from Springer, The International Society of Child Indicators (ISCI)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().