Constrained maximum likelihood estimation for two-level mean and covariance structure models

Peter M. Bentler, Jiajuan Liang, Man Lai TANG, Ke Hai Yuan

Research output: Contribution to journalJournal articlepeer-review

2 Citations (Scopus)


Maximum likelihood is commonly used for the estimation of model parameters in the analysis of two-level structural equation models. Constraints on model parameters could be encountered in some situations such as equal factor loadings for different factors. Linear constraints are the most common ones and they are relatively easy to handle in maximum likelihood analysis. Nonlinear constraints could be encountered in complicated applications. The authors develop an EM-type algorithm for estimating model parameters with both linear and nonlinear constraints. The empirical performance of the algorithm is demonstrated by a Monte Carlo study. Application of the algorithm for linear constraints is illustrated by setting up a two-level mean and covariance structure model for a real two-level data set and running an EQS program.

Original languageEnglish
Pages (from-to)325-345
Number of pages21
JournalEducational and Psychological Measurement
Issue number2
Publication statusPublished - Apr 2011

Scopus Subject Areas

  • Education
  • Developmental and Educational Psychology
  • Applied Psychology
  • Applied Mathematics

User-Defined Keywords

  • EM algorithm
  • linear and nonlinear constraints
  • maximum likelihood estimation
  • mean and covariance structure
  • two-level structural equation model


Dive into the research topics of 'Constrained maximum likelihood estimation for two-level mean and covariance structure models'. Together they form a unique fingerprint.

Cite this