Hierarchical linear models

Data are frequently structured so that observations at one level (e.g., an individual) are nested within units at another level (e.g., classes, schools, school districts). Models for such data are called hierarchical, or multilevel, or mixed models. Besides the obvious cases, hierarchical models are...

Full description

Saved in:
Bibliographic Details
Published inInternational Encyclopedia of Education pp. 568 - 574
Main Author Rindskopf, D.
Format Book Chapter
LanguageEnglish
Published Elsevier Ltd 2023
EditionFourth Edition
Subjects
Bayesian statistics
Growth models
Hierarchical models
Longitudinal data
Meta-analysis
Mixed models
Multicollinearity
Multilevel models
Nested data
Nonlinear models
Repeated measures
Shrinkage estimates
Shrinkage estimates
Nonlinear models
Repeated measures
Bayesian statistics
Multilevel models
Multicollinearity
Nested data
Longitudinal data
Hierarchical models
Growth models
Mixed models
Meta-analysis
Online AccessGet full text
ISBN0128186291
0128186305
9780128186305
9780128186299
DOI10.1016/B978-0-12-818630-5.10069-7

Cover

More Information
Summary:Data are frequently structured so that observations at one level (e.g., an individual) are nested within units at another level (e.g., classes, schools, school districts). Models for such data are called hierarchical, or multilevel, or mixed models. Besides the obvious cases, hierarchical models are used to analyze repeated measures or longitudinal data, viewing each observation as nested within an individual; and meta-analysis, viewing subjects as nested within studies. Multilevel data can be analyzed either using frequentist or Bayesian procedures, with the latter having particular advantages when there are few higher-level units.
ISBN:0128186291
0128186305
9780128186305
9780128186299
DOI:10.1016/B978-0-12-818630-5.10069-7