Bayesian Mixture Models with Weight-Dependent Component Priors
- 78 Downloads
In the conventional Bayesian mixture models, independent priors are often assigned to weights and component parameters. This may cause bias in estimation of missing group memberships due to the domination of these priors for some components when there is a big variation across component weights. To tackle this issue, we propose weight-dependent priors for component parameters. To implement the proposal, we develop a simple coordinate-wise updating algorithm for finding empirical Bayesian estimator of allocation or labelling vector of observations. We conduct a simulation study to show that the new method can outperform the existing approaches in terms of adjusted Rand index. The proposed method is further demonstrated by a real data analysis.
The research of Elaheh Oftadeh is supported by the 50th anniversary PhD scholarship from the University of Kent.
- 6.Raftery, A.E.: Hypothesis testing and model selection. In: Gilks, W.R., Spiegelhalter, D.J., Richardson, S. (eds.) Markov Chain Monte Carlo in Practice, pp. 163–188. Chapman and Hall, London (1996)Google Scholar