Spatial Autoregressive Modeling on Linear Mixed Models for Dependency Between Regions

This study develops a linear mixed model (LMM) that includes spatial effects between regions with autoregressive (SAR model). Between observations (regions) on LMM are usually assumed to be independent. However, these assumptions not always fulfilled due dependency regions. There two important parts in modeling: dependence and heterogeneity. In this study, we concerned the lag or SAR models because variables of interest is easier predict. On other hand, all real can directly seen from data patterns. addition, as challenge for researchers find estimators while values dependence, sampling variance, component variance unknown. aims parameter using numerical approach exact solutions. All obtained consistent estimators.