Using an EM Covariance Matrix to Estimate Structural Equation Models With Missing Data: Choosing an Adjusted Sample Size to Improve the Accuracy of Inferences
Authors:
- Craig K. EndersCECraig K. Enders
- James L. PeughJPJames L. Peugh
- 1 January 2004
- journal article
- Published by Taylor & Francis in Structural Equation Modeling: A Multidisciplinary Journal
- Vol. 11 (1) , 1-19
Abstract
Two methods, direct maximum likelihood (ML) and the expectation maximization (EM) algorithm, can be used to obtain ML parameter estimates for structural equation models with missing data (MD). Although the 2 methods frequently produce identical parameter estimates, it may be easier to satisfy missing at random assumptions using EM. However, no single value of N is applicable to the EM covariance matrix, and this may compromise inferences gained from the model fit statistic and parameter standard errors. The purpose of this study was to identify a value of N that provides accurate inferences when using EM. If all confirmatory factor analysis model indicators have MD, results suggest that the minimum N per covariance term yields honest Type 1 error rates. If MD are restricted to a subset of indicators, the minimum N per variance works well. With respect to standard errors, the harmonic mean N per variance term produces honest confidence interval coverage rates.Keywords
This publication has 7 references indexed in Scilit:
- Adding Missing-Data-Relevant Variables to FIML-Based Structural Equation ModelsStructural Equation Modeling: A Multidisciplinary Journal, 2003
- Missing data: Our view of the state of the art.Psychological Methods, 2002
- The Performance of the Full Information Maximum Likelihood Estimator in Multiple Regression Models With Missing DataEducational and Psychological Measurement, 2001
- The Relative Performance of Full Information Maximum Likelihood Estimation for Missing Data in Structural Equation ModelsStructural Equation Modeling: A Multidisciplinary Journal, 2001
- The impact of nonnormality on full information maximum-likelihood estimation for structural equation models with missing data.Psychological Methods, 2001
- A comparison of inclusive and restrictive strategies in modern missing data procedures.Psychological Methods, 2001
- Analysis with missing data in prevention research.1997