Factors associated with chronic child malnutrition in Ecuador. A study based on regression models and classification trees.

Authors

  • Pablo Flores Escuela Superior Politécnica de Chimborazo, Facultad de Ciencias, Grupo de Investigación en Ciencia de Datos, Riobamba, Ecuador.
  • Giorgina Congacha BASICALATAM SA, Human Data Department. Antonio de Ulloa N34-112, Quito, Ecuador

DOI:

https://doi.org/10.47187/perf.v1i26.132

Keywords:

Child malnutrition, ENSANUT, Regression, Decision trees

Abstract

This research seeks to determine significantly influencing factors on chronic malnutrition of children from zero to five years old in Ecuador. The variables that were part of the study have been considered according to the conceptual framework proposed by UNICEF and extracted from the databases of the latest 2018 Health and Nutrition survey developed by the National Institute of Statistics and Censuses and the Ministry of Public Health. In order to compare results, models based on classification trees and logistic regression were applied. It was found that the basic factors related to: child's ethnic group, mother's schooling, access to mobile communication, parents' marital status, mother's age, the number of children in the family, and the type of fuel used for cooking have a significant influence on the infant's nutritional status. These factors are directly related with basic and underlying factors such as control of the mother before and after delivery, infant vaccination, adequate nutrition and the size of the child at birth, which also influence in malnutrition.

Downloads

Download data is not yet available.

References

UNICEF. Estado mundial de la infancia 2008 - Resumen Ejecutivo: Supervivencia Infantil.: Unicef; 2007.

INEC. Boletín Técnico: Encuesta Nacional de Salud y Nutrición 2018. Quito - Ecuador.; 2019.

SENPLADES. Plan Nacional de Desarrollo 2017-2021. Toda una Vida Quito - Ecuador; 2017.

INEC. Encuesta Nacional de Salud y Nutrición ENSANUT. [Online]. [cited 2021 Enero. Available from: https://www.ecuadorencifras.gob.ec/salud-salud-reproductiva-y-nutricion/.

Trujillo M. Factores asociados a desnutrición crónica infantil en niños menores de cinco años de edad en el Perú: Sub-análisis de la Endes 2018. Universidad Ricardo Palma. 2020; 1(1).

Pérez J, Echavarría F. Árboles de clasificación vs regresión logística en el desarrollo de competencias genéricas en ingeniería. Computación y Sistemas. 2018; 22(4).

Demir E. A decision support tool for predicting patients at risk of readmission: A comparison of classification trees, logistic regression, generalized additive models, and multivariate adaptive regression splines. Decision Sciences. 2014; 45(5).

Charris L. Análisis comparativo de los algoritmos de árboles de decisión en el procesamiento de datos biológicos. Investigación y desarrollo en TIC. 2018; 9(1).

Andrade V, Flores P. Comparativa entre classification trees, random forest y gradient boosting; en la predicción de la satisfacción laboral en Ecuador. Ciencia Digital. 2018 Diciembre; 2(4).

UNICEF. Estado mundial de la infancia - Nutrición. New York: Fondo de las Naciones Unidas para la Infancia; 1998.

R CT. R: A Language and Environment for Statistical Computing. Vienna - Austria: R Foundation for Statistical Computing; 2020.

Kuhn M. caret: Classification and Regression Training. 2020. R package version 6.0-86.

Therneau T, Atkinson B. rpart: Recursive Partitioning and Regression Trees. 2019. R package version 4.1-15.

Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, et al. xgboost: Extreme Gradient Boosting. 2021. R package version 1.3.2.1.

Lunardon N, Giovanna M, Nicola T. ROSE: a Package for Binary Imbalanced Learning. R Journal. 2014; 6(1).

Maimon O, Rokach L. Data mining with decision trees: theory and applications: World scientific; 2014.

Breiman L. Classification and regression trees.: Wadsworth International Group; 1984.

Buntine W. Learning classification trees. Statistics and computing. 1992; 2(2).

Rokach L, Oded M. Classification trees. In Data mining and knowledge discovery handbook Boston: Springer; 2009.

Therneau T, Atkinson B. rpart: Recursive Partitioning and Regression Trees. 2019. R package version 4.1-15.

Hastie T, Tibshirani R, Friedman J. Boosting and additive trees. In The elements of statistical learning New York: Springer; 2009.

Elith J, hastie T. A working guide to boosted regression trees. Journal of Animal Ecology. 2008; 77(4).

tolles J, Meurer W. Logistic regression: relating patient characteristics to outcomes. Jama. 2016; 316(5).

Arocena V. Factores asociados a la Desnutrición Crónica Infantil en el Perú, 1996-2007. Instituto Nacional de Estadística e Informática. 2009 octubre.

Arocena V. Factores asociados a la desnutrición crónica infantil en Perú: una aplicación de modelos multinivel. Revista Latinoamericana de Población. 2010; 4(6).

Kühl A, Corso A, Leite M, Bastos J. Perfil nutricional e fatores associados à ocorrência de desnutrição entre crianças indígenas Kaingáng da Terra Indígena de Mangueirinha, Paraná, Brasil. Cadernos de Saúde Pública. 2009; 25.

Souza O, Benicio M, Castro T, Muniz P, Cardoso M. Desnutrição em crianças menores de 60 meses em dois municípios no Estado do Acre: prevalência e fatores associados. Revista brasileira de Epidemiologia. 2012; 15(1).

Généus W, Lachaud , Gayet I. Factores asociados al descenso de la desnutrición crónica de los niños de 6 a 24 meses en Haití en el período 1994-2017. Notas de Población. 2020.

Published

2021-09-09

How to Cite

Flores, P., & Congacha, G. (2021). Factors associated with chronic child malnutrition in Ecuador. A study based on regression models and classification trees. Perfiles, 1(26), 21-33. https://doi.org/10.47187/perf.v1i26.132