Finite Mixture of Heteroscedastic Single-Index Models  

作　　者：Peng Zeng 

机构地区：[1]不详

出　　处：《Open Journal of Statistics》2012年第1期12-20,共9页统计学期刊（英文）

摘　　要：In many applications a heterogeneous population consists of several subpopulations. When each subpopulation can be adequately modeled by a heteroscedastic single-index model, the whole population is characterized by a finite mixture of heteroscedastic single-index models. In this article, we propose an estimation algorithm for fitting this model, and discuss the implementation in detail. Simulation studies are used to demonstrate the performance of the algorithm, and a real example is used to illustrate the application of the model.In many applications a heterogeneous population consists of several subpopulations. When each subpopulation can be adequately modeled by a heteroscedastic single-index model, the whole population is characterized by a finite mixture of heteroscedastic single-index models. In this article, we propose an estimation algorithm for fitting this model, and discuss the implementation in detail. Simulation studies are used to demonstrate the performance of the algorithm, and a real example is used to illustrate the application of the model.

关 键 词：EM Algorithm Finite MIXTURE MODEL HETEROGENEITY HETEROSCEDASTICITY Local Linear SMOOTHING Single-Index MODEL 

分 类 号：O21[理学—概率论与数理统计]