APLIKASI REGRESI LOGISTIK ORDINAL MULTILEVEL UNTUK PEMODELAN DAN KLASIFIKASI HURUF MUTU MATA KULIAH METODE STATISTIKA

Statistical Methods (STK211) is an interdept course under coordination of Statistic Departement Faculty of Mathematics and Natural Science, Bogor Agricultural University (BAU). The final grade received by student who follow Statistical Methods is measurement in ordinal scale, that is A, B, C, D and E. In the 2008/2009 academic year there are 7 parallel classes in the Faculty of Mathematics and Natural Science, BAU. By considering the hierarchical structure contained in the score of student achievement data, the student (first level) is nested in a parallel class (second level), hence this study used multilevel ordinal logistic regression analysis to model the final score of Statistical Methods with the factors that influence it. Explanatory variables that significantly affect the final score of Statistical Methods are the GPA of TPB (student’s first year of college) and gender, with the variability of the intercepts across parallel classes in the logit function as 1.184. Percentage classification accuracy obtained by using multilevel ordinal logistic regression model was 56.85%Keywords : hierarchical, multilevel modeling, multilevel ordinal logistic regression, classificatio