报告人:马海强
时 间: 2021年11月25日14:30-15:30
地 点:腾讯会议 840519082
题 目: Pseudo-Bayesian Classified Mixed Model Prediction
摘 要：We propose a new classified mixed model prediction (CMMP) procedure, called pseudo-Bayesian CMMP, that utilizes network information in matching the group index between the training data and new data, whose characteristics of interest one wishes to predict. The current CMMP procedures (Jiang et al. 2018; Sun et al. 2018) do not incorporate such information; as a result, the methods are not consistent in terms of matching the group index. Although, as the number of training data groups increases, the current CMMP method can predict the mixed effects of interest consistently, its accuracy is not guaranteed when the number of groups is moderate, as is the case in many potential applications. The proposed pseudo-Bayesian CMMP procedure assumes a flexible working probability model for the group index of the new observation to match the index of a training data group, which may be viewed as a pseudo prior. We show that, given any working model satisfying mild conditions, the pseudo Bayesian CMMP procedure is consistent and asymptotically optimal both in term of matching the group index and in terms of predicting the mixed effect of interest associated with the new observations. The theoretical results are fully supported by results of empirical studies, including Monte-Carlo simulations and real-data validation.
报告人简介：
马海强，博士，江西财经大学统计学院硕士生导师，2016年毕业于复旦大学管理学院概率论与数理统计专业，师从朱仲义教授，主要的研究方向是函数型数据和分位数回归. 目前以第一作者在国内外统计学术期刊发表SCI学术论文8篇；先后主持国家自然科学基金青年项目(已结题)、国家自然科学基金地区项目(在研)、中国博士后面上项目各1项（在研），主持省部级项目4项。