## Bayesian Analysis

### Deviance information criteria for missing data models

#### Abstract

The deviance information criterion (DIC) introduced by Spiegelhalter et al.(2002) for model assessment and model comparison is directly inspired by linear and generalised linear models, but it is open to different possible variations in the setting of missing data models, depending in particular on whether or not the missing variables are treated as parameters. In this paper, we reassess the criterion for such models and compare different DIC constructions, testing the behaviour of these various extensions in the cases of mixtures of distributions and random effect models.

#### Article information

Source
Bayesian Anal., Volume 1, Number 4 (2006), 651-673.

Dates
First available in Project Euclid: 22 June 2012

https://projecteuclid.org/euclid.ba/1340370933

Digital Object Identifier
doi:10.1214/06-BA122

Mathematical Reviews number (MathSciNet)
MR2282197

Zentralblatt MATH identifier
1331.62329

#### Citation

Celeux, G.; Forbes, F.; Robert, C. P.; Titterington, D. M. Deviance information criteria for missing data models. Bayesian Anal. 1 (2006), no. 4, 651--673. doi:10.1214/06-BA122. https://projecteuclid.org/euclid.ba/1340370933

#### References

• Aitkin, M. (1991). "Posterior Bayes factors (with discussion)." Journal of the Royal Statistical Society, Series B, 53: 111–142.
• Bryant, P. and Williamson, J. A. (1978). "Asymptotic behaviour of lassification maximum likelihood estimates." Biometrika, 65: 273–281.
• Cappé, O., Moulines, E., and Rydén, T. (2005). Hidden Markov Models. New York: Springer-Verlag.
• Celeux, G., Hurn, M., and Robert, C. P. (2000). "Computational and inferential difficulties with mixture posterior distributions." Journal of the American Statistical Association, 95(3): 957–979.
• DeIorio, M. and Robert, C. P. (2002). "Discussion of Spiegelhalter et al." Journal of the Royal Statistical Society, Series B, 64: 629–630.
• Dempster, A., Laird, N., and Rubin, D. (1977). "Maximum likelihood from incomplete data via the EM" algorithm (with discussion). Journal of the Royal Statistical Society, Series B, 39: 1–38.
• Hodges, J. and Sargent, D. (2001). "Counting degrees of freedom in hierarchical and other richly-parameterised models." Biometrika, 88: 367–379.
• Little, R. and Rubin, D. (1987). Statistical Analysis with Missing Data. New York: J. Wiley.
• Little, R. J. A. and Rubin, D. B. (1983). "On jointly estimating parameters and missing data by maximizing the complete-data likelihood." American Statistician, 37: 218–220.
• Marin, J.-M., Mengersen, K., and Robert, C. (2005). "Bayesian Modelling and Inference on Mixtures of Distributions." In Rao, C. and Dey, D. (eds.), Handbook of Statistics, volume 25 (to appear). Springer-Verlag, New York.
• Marriott, F. H. C. (1975). "Separating mixtures of mixture distributions." Biometrics, 31: 767–769.
• McLachlan, G. and Krishnan, T. (1997). The EM Algorithm and Extensions. New York: J. Wiley.
• Richardson, S. (2002). "Discussion of Spiegelhalter et al." Journal of the Royal Statistical Society, Series B, 64: 631.
• Robert, C. P. (2001). The Bayesian Choice (second edition). Springer Verlag.
• Robert, C. P. and Casella, G. (2001). Monte Carlo Statistical Methods. New York: Springer Verlag, second edition.
• Roeder, K. (1990). "Density estimation with confidence sets exemplified by superclusters and voids in galaxies." Journal of the American Statistical Association, 85: 617–624.
• Spiegelhalter, D., Thomas, A., Best, N., and Lunn, D. (2004). "WinBUGS" 1.4 User Manual." Technical report, MRC Biostatistics Unit, Cambridge. http://www.mrc-bsu.cam.ac.uk/bugs/winbugs/manual14.pdf
• Spiegelhalter, D. J., Best, N., Carlin, B., and van der Linde, A. (2002). "Bayesian measures of model complexity and fit." Journal of the Royal Statistical Society, Series B, 64: 583–640.
• Stephens, M. (2000). "Dealing with Label Switching in Mixture Models." Journal of the Royal Statistical Society, Series B, 62: 795–809.
• van der Linde, A. (2004). "DIC" in variable selection." Technical report, Institute of Statistics, University of Bremen. http://www.math.uni-bremen.de/$\sim$avdl/download/paper s/varsel2.pdf