会议时间：2022/10/11 18:30-21:30 (GMT+08:00)中国标准时间-北京

点击链接入会，或添加至会议列表：https://meeting.tencent.com/dm/6gIFsfazIXeZ

腾讯会议：791-762-620

Functional concurrent hidden Markov models

This study considers a functional concurrent hidden Markov model. The proposed model consists of two components. One is a transition model for elucidating how potential covariates influence the transition probability from one state to another. The other is a conditional functional linear concurrent regression model for characterizing the state-specific effects of functional covariates. A distribution-free random effect is introduced to the conditional model todescribe the dependency of individual functional observations. The soft-thresholding operator and the adaptive group lasso are introduced to simultaneously accommodate the local and global sparsity of the functional coefficients. A Bayesian approach is developed to jointly conduct estimation, variable selection, and the detection of zero-effect regions. This proposed approach incorporates the dependent Dirichlet process with stick-breaking prior for accommodating the unspecified distribution of the random effect and a blocked Gibbs sampler for efficient posterior sampling. Finally, the empirical performance of the proposed method is evaluated through simulation studies, and the utility of the methodology is demonstrated by an application to the analysis of air pollution and meteorological data.

报告人简介：宋心远，香港中文大学统计系教授，香港中文大学理学院助理院长。宋心远教授的研究方向是潜变量模型，贝叶斯方法，统计计算和生存分析等。同时还担任多个国际期刊包括《Psychometrika》，《Biometrics》，《Computational Statistics & Data Analysis》和《Structural Equation Modeling: A Multidisciplinary Journal》的副主编或编委。已在国际期刊发表超过100篇论文，近期论文主要发表于《Journal of the American Statistical Association》，《Biometrika》，《Biometrics》，《Bioinformatics》，《Psychometrika》，《Quantitative Finance》等期刊、并主持超过10项香港研究资助局和国家自然科学基金委资助项目。