×

The effect of misspecifying the random-effects distribution in linear mixed models for longitudinal data. (English) Zbl 0900.62374

Summary: Maximum likelihood estimators for fixed effects and variance components in linear mixed models, obtained under the assumption of normally distributed random effects, are shown to be consistent and asymptotically normally distributed, even when the random-effects distribution is not normal. However, a sandwich-type correction to the inverse Fisher information matrix is then needed in order to get the correct asymptotic covariance matrix. Extensive simulations show that the so-obtained corrected standard errors are clearly superior to the naive uncorrected ones, especially for the parameters in the random-effects covariance matrix, even in moderate samples.

MSC:

62J10 Analysis of variance and covariance (ANOVA)
62F10 Point estimation
65C99 Probabilistic methods, stochastic differential equations
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Softwar, Bmdp Statistical; Inc.: 1440 sepulveda boulevard suite 316, Los Angeles, CA 90025. BMDP statistical software manual 2 (1990)
[2] Butler, S. M.; Louis, T. A.: Random effects models with non-parametric priors. Statist. med. 11, 1981-2000 (1992)
[3] Fahrmeir, L.; Kaufmann, H.: Consistency and asymptotic normality of the maximum likelihood estimator in generalized models. Ann. statist. 13, 342-368 (1985) · Zbl 0594.62058
[4] Firth, D.: Recent developments in quasi-likelihood methods. Proc. ISI 49th session, 341-358 (1993)
[5] Goldstein, H.: The design and analysis of longitudinal studies. Their role in the measurement of change. (1979) · Zbl 0492.62092
[6] Golub, G. H.; Van Loan, C. F.: Matrix computations. (1989) · Zbl 0733.65016
[7] Johnson, N. L.; Kotz, S.: Continuous univariate distributions – 1. (1970) · Zbl 0213.21101
[8] Liang, K. Y.; Zeger, S. L.: Longitudinal data analysis using generalized linear models. Biometrika 73, 13-22 (1986) · Zbl 0595.62110
[9] Lindstrom, M. J.; Bates, D. M.: Newton-raphson and EM algorithms for linear mixed-effects models for repeated-measures data. J. amer. Statist. assoc. 83, 1014-1022 (1988) · Zbl 0671.65119
[10] Inc., Sas Institute; Cary, Nc: SAS technical report P-229. (1992)
[11] Seber, G. A. F.: Multivariate observations. (1984) · Zbl 0627.62052
[12] Sharples, K.; Breslow, N. E.: Regression analysis of correlated binary data: some small sample results for the estimating equation approach. J. statist. Comput. simulation 42, 1-20 (1992) · Zbl 0775.62203
[13] Verbeke, G.; Lesaffre, E.: Large sample properties of the maximum likelihood estimators in linear mixed models with misspecified random-effects distributions. Technical report, report #1996.1 (1994)
[14] Verbeke, G.; Lesaffre, E.: A linear mixed-effects model with heterogeneity in the random-effects population. J. amer. Statist. assoc. 91, 217-221 (1996) · Zbl 0870.62057
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.