Predicting academic performance based on students' family environment: Evidence for Colombia using classification trees

Abstract

Family environment, parental economic and social conditions influence students' academic performance. However, in Colombia, research and methods that have been used to study these variables are rather limited. This research predicts the academic performance of students who took the 2016 State exam for access to higher education (Saber 11) based on observations and characteristics of the students' families. The data comes from the database of the Colombian Institute Educational Evaluation (ICFES), and classification trees are generated in order to predict academic results. The results show that the family variables that best predict academic results are, respectively, the educational level of the mother, the socioeconomic stratum of the household, the number of books in the home, the educational level of the father and the presence of a computer in the household.