Penerapan model regresi multilevel untuk data ketepatan waktu lulus mahasiswa

Abstract

Multilevel logistic regression is one of the alternatives to solving a problem that has a nested data structure like the student data in Alauddin in 2016. The data indicates that students are nested in each different study program. This condition allows the students in the same study program tend to have similar characteristics. The study aims to gain a student graduating model of punctuality using multilevel regression analysis and recognize factors that have a significant impact on student graduating time. Based on our research, we find the best model that fits the data to be the random intercepts model with a random slope of gender variable. The variables that have significant effects are gender, cumulative achievement index, educational background, and accredited program. Keywords: logistic regression, nested, multilevel logistic regression, graduation of student MSC2020: 62J05