On Normal Theory Based Inference for Multilevel Models with Distributional Violations
Authors:
- 1 December 2002
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 67 (4) , 539-561
Abstract
Data in social and behavioral sciences are often hierarchically organized though seldom normal, yet normal theory based inference procedures are routinely used for analyzing multilevel models. Based on this observation, simple adjustments to normal theory based results are proposed to minimize the consequences of violating normality assumptions. For characterizing the distribution of parameter estimates, sandwich-type covariance matrices are derived. Standard errors based on these covariance matrices remain consistent under distributional violations. Implications of various covariance estimators are also discussed. For evaluating the quality of a multilevel model, a rescaled statistic is given for both the hierarchical linear model and the hierarchical structural equation model. The rescaled statistic, improving the likelihood ratio statistic by estimating one extra parameter, approaches the same mean as its reference distribution. A simulation study with a 2-level factor model implies that the rescaled statistic is preferable.Keywords
This publication has 42 references indexed in Scilit:
- On Estimating Standard Errors in Multilevel AnalysisJournal of the Royal Statistical Society: Series D (The Statistician), 2000
- Multilevel Covariance Structure AnalysisSociological Methods & Research, 1994
- Can test statistics in covariance structure analysis be trusted?Psychological Bulletin, 1992
- Asymptotic Chi-Square Tests for a Large Class of Factor Analysis ModelsThe Annals of Statistics, 1990
- The Asymptotic Normal Distribution of Estimators in Factor Analysis under General ConditionsThe Annals of Statistics, 1988
- Analysis of Covariance Structures under Elliptical DistributionsJournal of the American Statistical Association, 1987
- Longitudinal data analysis using generalized linear modelsBiometrika, 1986
- Consequences and Detection of Misspecified Nonlinear Regression ModelsJournal of the American Statistical Association, 1981
- Asymptotic distributions in canonical correlation analysis and other multivariate procedures for nonnormal populationsBiometrika, 1980
- Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher informationBiometrika, 1978