Search
- Browse Authors in the The University of Michigan Department of Biostatistics Working Paper Series
Notification
Most popular papers
COBRA Notification
Most Popular Papers
Institutions: Join COBRA
About COBRA
- Composite likelihood Bayesian information criteria for model selection in high dimensional data
-
-
Download the Paper
Forward to a colleague
- Abstract:
- For high-dimensional data set with complicated dependency structures, the full likelihood
approach often renders to intractable computational complexity. This imposes diąculty on
model selection as most of the traditionally used information criteria require the evaluation
of the full likelihood. We propose a composite likelihood version of the Bayesian information
criterion (BIC) and establish its consistency property for the selection of the true underlying
model. Under some mild regularity conditions, the proposed BIC is shown to be selection
consistent, where the number of potential model parameters is allowed to increase to inŻnity
at a certain rate of the sample size. Simulation studies demonstrate the empirical performance
of this new BIC criterion, especially for the scenario that the number of parameters increases
with the sample size.
- Subject Area:
- General Biostatistics
- Suggested Citation:
- X Gao and Peter Xuekun Song,
"Composite likelihood Bayesian information criteria for model selection in high dimensional data"
(April 2009).
The University of Michigan Department of Biostatistics Working Paper Series.
Working Paper 79.
http://www.bepress.com/umichbiostat/paper79