Application of Hierarchical Linear Models/Linear Mixed-effects Models in School Effectiveness Research

Abstract

Multilevel data are very common in educational research. Hierarchical linear models/linear mixed-effects models (HLMs/LMEs) are often utilized to analyze multilevel data nowadays. This paper discusses the problems of utilizing ordinary regressions for modeling multilevel educational data, compare the data analytic results from three regression techniques, and demonstrate the appropriate use of HLMs/LMEs in school effectiveness research. An analysis of a subset of NELS-88 data in which students are nested within schools is used to illustrate features of HLMs/LMEs, relative to both student-level analysis that ignores the hierarchy of the dataset, and school-level analysis that aggregate the student-level units. The features and advantages of HLMs/LMEs in multilevel educational data analysis are discussed. Some guidelines, caveats, suggestions and recommendations in utilizing HLMs/LMEs for analyzing multilevel educational data are highlighted.