Multivariate mixtures of normals with unknown number of components
Multivariate mixtures of normals with unknown number of components
复制标题
DOI：
10.1007/s11222-006-5338-6
复制
发表时间：
2006-03-01
影响因子：
2.2
通讯作者：
Papageorgiou, I
中科院分区：
文献类型：
--
作者：
Dellaportas, P;Papageorgiou, I
我们提出了完整的贝叶斯分析的有限混合物的多元正态未知数量的组件。我们采用可逆跳马尔可夫链蒙特卡罗，我们构建，在一个类似的方式理查森和绿色（1997），分裂和合并移动，产生良好的混合马尔可夫链。在当前协方差矩阵的特征向量和特征值空间上构造分裂移动，使得所提出的协方差矩阵是正定的。我们提出的方法在分类和歧视，以及异质性建模的应用。我们测试我们的算法与真实的和模拟数据。
We present full Bayesian analysis of finite mixtures of multivariate normals with unknown number of components. We adopt reversible jump Markov chain Monte Carlo and we construct, in a manner similar to that of Richardson and Green (1997), split and merge moves that produce good mixing of the Markov chains. The split moves are constructed on the space of eigenvectors and eigenvalues of the current covariance matrix so that the proposed covariance matrices are positive definite. Our proposed methodology has applications in classification and discrimination as well as heterogeneity modelling. We test our algorithm with real and simulated data.