DIC: Deviance information criterion

In BayesianTools: General-Purpose MCMC and SMC Samplers and Tools for Bayesian Statistics

Deviance information criterion

Description

Deviance information criterion

Usage

DIC(sampler, ...)

Arguments

sampler	An object of class bayesianOutput (mcmcSampler, smcSampler, or mcmcList)
...	further arguments passed to getSample

Details

Output: list with the following elements:
DIC : Deviance Information Criterion
IC : Bayesian Predictive Information Criterion
pD : Effective number of parameters (pD = Dbar - Dhat)
pV : Effective number of parameters (pV = var(D)/2)
Dbar : Expected value of the deviance over the posterior
Dhat : Deviance at the mean posterior estimate

Author(s)

Florian Hartig

References

Spiegelhalter, D. J.; Best, N. G.; Carlin, B. P. & van der Linde, A. (2002) Bayesian measures of model complexity and fit. J. Roy. Stat. Soc. B, 64, 583-639.

Gelman, A.; Hwang, J. & Vehtari, A. (2014) Understanding predictive information criteria for Bayesian models. Statistics and Computing, Springer US, 24, 997-1016-.

See Also

WAIC, MAP, marginalLikelihood

BayesianTools documentation built on Feb. 16, 2023, 8:44 p.m.