Vera Maya Santi, Khairil Anwar Notodiputro, Indahwati, Bagus Sartono, Budi Susetyo, Anang Kurnia
This research is motivated by complex data problems such as longitudinal data structures, multivariate response variables, and hierarchical random effects. These problems must be addressed to answer substantive questions regarding the interrelated change problem between the measurement time and the variance at each level. A random effect is more problematic when a random hierarchical impact has some fixed effects. The basic model was introduced, i.e., a multivariate linear mixed model for longitudinal data, while a multilevel performance model was introduced for hierarchical data structures. This study proposes to develop a MLMM with two-level random effects on the nested data structure, namely the multilevel multivariate linear mixed model (MMLMM). The initial stage of this research involves deriving an analytical formula for parameter estimation within the model. The performance of the model is examined through the RMSEp, bias, and the consistency of the parameter coefficients. To evaluate the effectiveness of the proposed model, a simulationbased analysis was conducted. For an empirical study, MMLMM was applied to the average natural sciences major of high school national exam in West Java Province, Indonesia. Applying the proposed model to actual data shows that the standard error of the national exam average predicted score tends to be smaller when compared to the standard model. © 2026, International Association of Engineers. All rights reserved.
Statistics Study Programme, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta, Jakarta Timur, 13220, Indonesia; Statistics and Data Science, Department of Statistics, IPB University, Bogor, 16680, Indonesia; School of Data Science, Mathematics, and Informatics, IPB University, Bogor, 16680, Indonesia; Statistics and Data Science, IPB University, Bogor, 16680, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock