Efficient Parametrisations for Normal Linear Mixed Models
Alan E. Gelfand, Sujit K. Sahu, Bradley P. Carlin · Biometrika · 1995
The generality and easy programmability of modern sampling-based methods for maximisation of likelihoods and summarisation of posterior distributions have led to a tremendous increase in the complexity and dimensionality of the statistical models used in practice. However, these methods can often be extremely slow to converge, due to high correlations between, or weak identifiability of, certain model parameters. We present simple hierarchical centring reparametrisations that often give improved convergence for a broad class of normal linear mixed models. In particular, we study the two-stage hierarchical normal linear model, the Laird-Ware model for longitudinal data, and a general structure for hierarchically nested linear models. Using analytical arguments, simulation studies, and an example involving clinical markers of acquired immune deficiency syndrome (aids), we indicate when reparametrisation is likely to provide substantial gains in efficiency.
Cited by 304 works. doi:10.1093/biomet/82.3.479
Authors
References
- Linear Statistical Inference and its Applications
- Random-Effects Models for Longitudinal Data
- Linear Statistical Inference and Its Applications.
- Inference from Iterative Simulation Using Multiple Sequences
- Bayes Estimates for the Linear Model
- Approximate Inference in Generalized Linear Mixed Models
- Multilevel Mixed Linear Model Analysis Using Iterative Generalized Least Squares
- Covariance Structure of the Gibbs Sampler with Applications to the Comparisons of Estimators and Augmentation Schemes
- Spatial statistics and Bayesian computation (with discussion)
- A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects