Markov chain Monte Carlo (MCMC) enables fitting complex hierarchical models that may adequately reflect the process of data generation. Some of these models may contain more parameters than can be uniquely inferred from the distribution of the data, causing non-identifiability. The reaction norm model with unknown covariates (RNUC) is a model in which unknown environmental effects can be inferred jointly with the remaining parameters. The problem of identifiability of parameters at the level of the likelihood and the associated behaviour of MCMC chains were discussed using the RNUC as an example. It was shown theoretically that when environmental effects (covariates) are considered as random effects, estimable functions of the fixed effects, (co)variance components and genetic effects are identifiable as well as the environmental effects. When the environmental effects are treated as fixed and there are other fixed factors in the model, the contrasts involving environmental effects, the variance of environmental sensitivities (genetic slopes) and the residual variance are the only identifiable parameters. These different identifiability scenarios were generated by changing the formulation of the model and the structure of the data and the models were then implemented via MCMC. The output of MCMC sampling schemes was interpreted in the light of the theoretical findings. The erratic behaviour of the MCMC chains was shown to be associated with identifiability problems in the likelihood, despite propriety of posterior distributions, achieved by arbitrarily chosen uniform (bounded) priors. In some cases, very long chains were needed before the pattern of behaviour of the chain may signal the existence of problems. The paper serves as a warning concerning the implementation of complex models where identifiability problems can be difficult to detect a priori. We conclude that it would be good practice to experiment with a proposed model and to understand its features before embarking on a full MCMC implementation.
[1]
J. Jensen,et al.
Genotype by Environment Interaction in Nordic Dairy Cattle Studied Using Reaction Norms
,
2002
.
[2]
M. Lund,et al.
Bayesian analysis of the linear reaction norm model with unknown covariates.
,
2006,
Journal of animal science.
[3]
A. Gelfand,et al.
Identifiability, Improper Priors, and Gibbs Sampling for Generalized Linear Models
,
1999
.
[4]
Charles J. Geyer,et al.
Practical Markov Chain Monte Carlo
,
1992
.
[5]
A. Rebaï,et al.
Méthodes mathématiques pour l'étude des gènes contrôlant des caractères quantitatifs
,
1994,
Genetics Selection Evolution.
[6]
B. Carlin,et al.
Identifiability and convergence issues for Markov chain Monte Carlo fitting of spatial models.
,
2000,
Statistics in medicine.
[7]
George Casella,et al.
Functional Compatibility, Markov Chains and Gibbs Sampling with Improper Posteriors
,
1998
.
[8]
G. Casella,et al.
The Effect of Improper Priors on Gibbs Sampling in Hierarchical Linear Mixed Models
,
1996
.
[9]
Dale J. Poirier,et al.
REVISING BELIEFS IN NONIDENTIFIED MODELS
,
1998,
Econometric Theory.
[10]
T. Swartz,et al.
Bayesian identifiability and misclassification in multinomial data
,
2004
.
[11]
T. Rothenberg.
Identification in Parametric Models
,
1971
.
[12]
D. Gianola,et al.
Marginal inferences about variance components in a mixed linear model using Gibbs sampling
,
1993,
Genetics Selection Evolution.