The Effect of Small Sample Size on Two-Level Model Estimates: A Review and Illustration

Daniel M. McNeish, Laura M. Stapleton

Research output: Contribution to journalReview article

157 Scopus citations

Abstract

Multilevel models are an increasingly popular method to analyze data that originate from a clustered or hierarchical structure. To effectively utilize multilevel models, one must have an adequately large number of clusters; otherwise, some model parameters will be estimated with bias. The goals for this paper are to (1) raise awareness of the problems associated with a small number of clusters, (2) review previous studies on multilevel models with a small number of clusters, (3) to provide an illustrative simulation to demonstrate how a simple model becomes adversely affected by small numbers of clusters, (4) to provide researchers with remedies if they encounter clustered data with a small number of clusters, and (5) to outline methodological topics that have yet to be addressed in the literature.

Original languageEnglish (US)
Pages (from-to)295-314
Number of pages20
JournalEducational Psychology Review
Volume28
Issue number2
DOIs
StatePublished - Jun 1 2016
Externally publishedYes

Keywords

  • HLM
  • Mixed model
  • Multilevel model
  • Small number of clusters
  • Small sample

ASJC Scopus subject areas

  • Developmental and Educational Psychology

Fingerprint Dive into the research topics of 'The Effect of Small Sample Size on Two-Level Model Estimates: A Review and Illustration'. Together they form a unique fingerprint.

  • Cite this