A generalized linear mixed model for understanding determinant factors of student's interest in pursuing bachelor's degree at Universitas Syiah Kuala

Generalized Linear Mixed Model (GLMM) is a framework that has response variable, fixed effects, and random effects. The variable comes from an exponential family, whereas effects have normal distribution. Estimating parameters can be calculated using the maximum likelihood method Laplace approach or Gauss-Hermite Quadrature (GHQ) approach. purpose of this study was to identify factors trigger student's interest continue studying at Universitas Syiah Kuala (USK) both techniques. GLMM suitable for data because Bernoulli distribution, are assumed having Also, model helps relationship between dependent predictors. This utilizes six high schools in Banda Aceh city drawn two-stage sampling technique. Stage 1, we randomly chose out sixteen public senior Aceh. 2, selected students each school four different major classes. includes one binary five numerical fixed-effects, two USK (yes no). including scores collaboration (C), Action (A), Emotion (E), Purposes (P), Hope (H). Finally, (S) majors (M). In study, GHQ techniques produce identical results. predictors explain student A, E, H. These positive effect. not significantly zero. with three significant better than complete predictor model.