Application of Multinomial Logistic Regression to analyze learning difficulties in statistics courses

Abstract

Every student basically wants to get the opportunity to achieve satisfactory academic performance. But from daily reality, it seems clear that students have differences in intellectual abilities, physical abilities, family background, habits and learning approaches that are sometimes very striking between a student and other students. The data used in this study consisted of primary data and secondary data. Primary data in the form of a questionnaire for the dependent variable and response variable. While secondary data contains general information on the number of students in the fourth semester of economic education courses obtained from the administration of the faculty of education, Unindra. Data analysis using multinomial logistic regression analysis. Based on the results of this study, independent variables that influence student learning difficulties in Statistics courses include; gender, regional origin, learning motivation, and learning resources. While the variables that did not have a significant effect on learning difficulties include; major at school, monthly tuition allowance, and study patterns. Furthermore, the value of the accuracy of the classification of students produced using multinomial logistic regression analysis of seventy-six point five percent.