FAKTOR – FAKTOR YANG MEMPENGARUHI INDEKS PRESTASI KUMULATIF MAHASISWA JURUSAN MATEMATIKA TAHUN MASUK 2017 FMIPA UNP MENGGUNAKAN ANALISIS REGRESI LOGISTIK MULTINOMIAL

Abstract

In higher education the reference used to determine student academic
achievement can be seen through the Grade Point Average (GPA). In
accordance with the vision of the Department of Mathematics students are
required to be more active in the learning process so that it will support
student academic achievement. But there are still students with obstacles in the learning process. Student GPA is influenced by many factors. The
factors causing these students to get a GPA include gender, entrance to
tertiary institutions, choice of majors, scholarships, place of residence, area
of origin, study methods, length of study, living expenses per month, and
organizational activity. For this reason, a model needs to be formed
because the model can be understood, explained, controlled, and predicted so that it can be determined what factors affect academic achievement. The purpose of this study is to determine the logistic regression model that describes the factors that affect the GPA of the Mathematics and Natural Sciences Department Students of FMIPA UNP.
The data used in this study are primary data with questionnaire data
collection tools. The population in this study was the 2017 Department of
Mathematics students with a sample size of 189 people. Analysis of the data used is multinomial logistic regression analysis.
Based on the results of the study, if 2 ≤ GPA <2.75 is used as a reference,
then the model obtained for GPA ≥ 3.50 is = 2,856 − 1,529 − 2,270 − 2,836 − 2,467 − 0,670 − 0,925 + 1,033 and the model for 2.75 ≤ GPA < 3.50 is = 2,039 − 1,533 − 0,918 − 1,237 − 0,609 + 0,081 + 0,863 + 1,628. The independent variables that have a significant effect are gender, majors, residence and monthly living costs

Keywords: Grade Point Average, Multinomial Logistic Regression