Accuracy of Laplace approximation for discrete response mixed models. (English) Zbl 1452.62537
Summary: The Laplace approximation is amongst the computational methods used for estimation in generalized linear mixed models. It is computationally the fastest, but there hasn’t been a clear analysis of when its accuracy is adequate. In this paper, for a few factors we do calculations for a variety of mixed models to show patterns in the asymptotic bias of the estimator based on the maximum of the Laplace approximation of the log-likelihood. The biggest factor for asymptotic bias is the amount of discreteness in the response variable; there is more bias for binary and ordinal responses than for a count response, and more bias for a count response when its support is mainly near 0. When there is bias, the bias decreases as the cluster size increases. Often, the Laplace approximation is adequate even for small cluster sizes. Even with bias, the Laplace approximation may be adequate for quick assessment of competing mixed models with different random effects and covariates.
MSC:
| 62J12 | Generalized linear models (logistic models) |
| 62-08 | Computational methods for problems pertaining to statistics |
References:
| [1] | Breslow, N. E.; Lin, X., Bias correction in generalized linear mixed models with a single component of dispersion, Biometrika, 82, 81-91 (1995) · Zbl 0823.62059 |
| [2] | Clarkson, D. B.; Zhan, Y., Using spherical-radial quadrature to fit generalized linear mixed effects models, J. Comput. Graph. Statist., 11, 639-659 (2002) |
| [3] | Davidian, M.; Giltinan, D. M., Nonlinear models for repeated measurements: An overview and update, J. Agric. Biol. Environ. Stat., 8, 387-419 (2003) |
| [4] | Demidenko, E., Mixed Models : Theory and Applications (2004), Wiley: Wiley New York · Zbl 1055.62086 |
| [5] | Engel, B., A simple illustration of the failure of PQL, IRREML, and APHL as approximate ML methods for mixed models for binary data, Biom. J., 40, 141-154 (1998) · Zbl 0899.62087 |
| [6] | Hedeker, D.; Gibbons, R. D., Longitudinal Data Analysis (2006), Wiley: Wiley New York · Zbl 1136.62075 |
| [7] | Lee, Y.; Nelder, J. A., Hierarchical generalized linear models (with discussion), J. Roy. Statist. Soc. B, 58, 619-678 (1996) · Zbl 0880.62076 |
| [8] | Lee, Y.; Nelder, J. A.; Pawitan, Y., Generalized Linear Models with Random Effect: Unified Analysis with H-likelihood (2006), CRC/Chapman & Hall: CRC/Chapman & Hall London · Zbl 1110.62092 |
| [9] | McCulloch, C. E.; Searle, S. R., Generalized, Linear, and Mixed Models (2001), Wiley: Wiley New York · Zbl 0964.62061 |
| [10] | Nash, J. C., Compact Numerical Methods for Computers: Linear Algebra and Function Minimisation (1990), Hilger: Hilger New York · Zbl 0697.68004 |
| [11] | Noh, M.; Lee, Y., REML estimation for binary data in GLMMs, J. Multivariate Anal., 98, 896-915 (2007) · Zbl 1113.62087 |
| [12] | Pinheiro, J. C.; Bates, D. M., Approximations to the log-likelihood function in the nonlinear mixed-effects model, J. Comput. Graph. Statist., 4, 12-35 (1995) |
| [13] | Pinheiro, J. C.; Chao, E. C., Efficient Laplacian and adaptive Gaussian quadrature algorithms for multilevel generalized linear mixed models, J. Comput. Graph. Statist., 15, 58-81 (2006) |
| [14] | Raudenbush, S. W.; Yang, M. L.; Yosef, M., Maximum likelihood for generalized linear models with nested random effects via high-order, multivariate Laplace approximation, J. Comput. Graph. Statist., 9, 141-157 (2000) |
| [15] | Renard, D.; Molenberghs, G.; Geys, H., A pairwise likelihood approach to estimation in multilevel probit models, Comput. Statist. Data Anal., 44, 649-667 (2004) · Zbl 1429.62324 |
| [16] | Stroud, A. H.; Secrest, D., Gaussian Quadrature Formulas (1996), Prentice-Hall: Prentice-Hall Englewood Cliffs, NJ · Zbl 0156.17002 |
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
