Poverty modeling of regencies/municipalities in the island of Sumatera

• Published in: Journal of physics. Conference series Vol. 1188; no. 1; pp. 12011 - 12018
• Main Authors: Rini, D S, Agustina, D, Sriliana, I, Novianti, P
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.03.2019
• Subjects: Drinking water; Life expectancy; Municipalities; Poverty; Regression models; Variables
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1188/1/012011

Binary logistic regression is a method used to explain the relationship between response variables that have two categories with one or more predictor variables that have a numerical or categorical scale. This research uses binary logistic regression to model and determine the factors that influence poverty in regencies/municipalities of Sumatera Island. In 2016, the percentage of poor people in Sumatera Island was third in Indonesia at 11.03 percent, so this problem needs to be studied further. The data used in this research is obtained from Central Bureau of Statistics in 2016. The response variable is binary where 0 for poor and 1 for not poor and also six predictor variables which include the percentage of Net Enrollment Rate, percentage of Expected Years of Schooling, percentage of GRDP Growth Rates, percentage of Per capita Average Expenditure for Food, percentage of Improved Drinking Water, and percentage of Life Expectancy. Based on this research, binary logistic regression model is giving a percentage of classification of 69.5 percent. Other than that percentage of Life Expectancy significantly affects poverty on the island of Sumatera.