Análisis de la obesidad en los adultos ecuatorianos. Una aplicación de regresión Poisson y regresión Logística

Published in: Industry, Innovation, and Infrastructure for Sustainable Cities and Communities: Proceedings of the 17th LACCEI International Multi-Conference for Engineering, Education and Technology
Date of Conference: July 24-26, 2019
Location of Conference: Montego Bay, Jamaica
Authors: Sandra García-Bustos (Escuela Superior Politécnica del Litoral, EC)
Nadia Cárdenas-Escobar (Escuela Superior Politécnica del Litoral, EC)
Iris Bustamante (Escuela Superior Politécnica del Litoral, EC)
Stefany Uguña Salazar (Escuela Superior Politécnica del Litoral, EC)
Kevin Peralta Rizzo (Escuela Superior Politécnica del Litoral, EC)
(Escuela Superior Politécnica del Litoral)
Full Paper: #401

Abstract:

Obesity is a disease which affects around 650 million people worldwide and more than 4.5 million in Ecuador. These figures are alarming because it is recognized as a significant factor in the non-communicable chronic diseases, which appear in all age groups. This work focusses on finding the relations between obesity depicted by Body Mass Index (BMI) and other variables such as gender, province, age group and geographic area for adults between 19 and 59 years old. To achieve this purpose, Logistic and Poisson regression models have been applied, and these results were significant in both models. After contrast pseudo 𝑅2, the best model has been identified as logistic regression due to its best fit and prediction. As a result, it has been obtained that for an adult male who lives in a rural area of Guayas, the possibility of being obese decreases by 78%. Furthermore, it can be affirmed that if an individual who lives in the province of Guayas moves to the province of Pichincha, and the rest of variables remain constant, then the possibility of being obese declines by 31%.