报告地点：翡翠科教楼A座第五会议室

举办单位：华体会网页入口

报告一：Distributed Empirical Likelihood Inference with or Without Byzantine Failures

报告华体会（中国）官方：2024年12月13日（星期五）8:10-8:40

报  告  人：王启华 教授

工作单位：中国科学院数学与系统科学研究院

报告简介：Empirical likelihood is a very important nonparametric approach that is of wide application. However, it is hard and even infeasible to calculate the empirical log-likelihood ratio statistic with massive data. The main challenge is the calculation of the Lagrange multiplier. This motivates us to develop a distributed empirical likelihood method by calculating the Lagrange multiplier in a multi-round distributed manner. It is shown that the distributed empirical log-likelihood ratio statistic is asymptotically standard chi-squared under some mild conditions. The proposed algorithm is communication-efficient and achieves the desired accuracy in a few rounds. Further, the distributed empirical likelihood method is extended to the case of Byzantine failures. A machine selection algorithm is developed to identify the worker machines without Byzantine failures such that the distributed empirical likelihood method can be applied. The proposed methods are evaluated by numerical simulations and illustrated with an analysis of airline on-time performance study and a surface climate analysis of Yangtze River Economic Belt

报告人简介：王启华，中国科学院数学与系统科学研究院研究员，博士生导师，国家杰出青年基金获得者，教育部长江学者奖励计划特聘教授，中科院“百人计划”入选者。曾在北京大学、香港大学任教。先后访问加拿大、美国、德国及澳大利亚10多所世界一流大学。主要从事复杂数据经验似然统计推断、缺失数据分析、高维数据统计分析、大规模数据分析等方面的研究，出版专著三部，在The Annals of Statistics, JASA及Biometrika等国际重要刊物发表论文140余篇,部分工作已产生持久的学术影响。

报告二：Bootstrap Model Averaging

报告华体会（中国）官方：2024年12月13日（星期五）8:40-9:10

报  告  人：邹国华 教授

工作单位：首都师范大学

报告简介：Model averaging has gained significant attention in recent years due to its ability of fusing information from different models. The critical challenge in frequentist model averaging is the choice of weight vector. The bootstrap method, known for its favorable properties, presents a new solution. In this paper, we propose a bootstrap model averaging approach that selects the weights by minimizing a bootstrap criterion. We demonstrate that the resultant estimator is asymptotically optimal in the sense that it achieves the lowest possible squared error loss. Furthermore, we establish the convergence rate of bootstrap weights tending to the theoretically optimal weights. Additionally, we derive the limiting distribution of our proposed model averaging estimator. By simulation studies and empirical applications, we show that our proposed method often has better performance than other commonly used model selection and model averaging methods.

报告人简介：邹国华，首都师范大学教授。博士毕业于中国科学院系统科学研究所，是国家杰出青年基金获得者、“新世纪百千万人才工程”国家级人选、中国科学院“百人计划”入选者、享受国务院政府特殊津贴，获中国科学院优秀研究生指导教师称号。

主要从事统计学的理论研究及其在经济金融、生物医学中的应用研究工作，在统计模型选择与平均、抽样调查的设计与分析、决策函数的优良性、疾病与基因的关联分析等方面的研究中取得了一系列重要成果，得到了国内外同行的好评与肯定，并被广泛引用。共出版教材2本，发表学术论文140余篇；主持和参加过近30项国家科学基金项目以及全国性的实际课题，提出的预测方法被实际部门所采用。

报告三：Flexible Bayesian Quantile Regression based on the Generalized Asymmetric Huberisedtype Distribution

报告华体会（中国）官方：2024年12月13日（星期五）9:10-9：40

报  告  人：张伟平 教授

工作单位：中国科学技术大学

报告简介：To alleviate the limitations in the flexibility of Bayesian quantile

regression models with an asymmetric Laplace (AL) or asymmetric

Huberised-type (AH) error, such as lack of changeable mode, diminishing

influence of outliers, and asymmetry and skewness under median

regression, we propose a new generalized AH distribution which is achieved through a hierarchical mixture representation, thus leading to a flexible Bayesian Huberised quantile regression framework. With many parameters in the model, we develop an efficient Markov chain Monte Carlo (MCMC) procedure based on the Metropolis-within-Gibbs sampling algorithm. To evaluate the efficacy of the new distribution, we conduct a thorough investigation of its flexibility and robustness through a series of simulation experiments. Finally, the proposed approach is applied to two empirical studies to demonstrate its superior model fit and prediction performance in comparison to existing approaches.

报告人简介：张伟平，中国科学技术大学教授，博导。主要从事纵向数据分析、贝叶斯统计、统计学习等领域中的统计理论和应用研究工作，先后在国内外学术期刊发表论文70余篇。主持了国家自然科学基金项目、重点项目和重点研发计划子课题等多个项目。担任全国工业统计学教学研究会与中国现场统计研究会等学会的常务理事。

报告四：Estimation in partially linear additive errors-in-variables model with stochastic linear restrictions

报告华体会（中国）官方：2024年12月13日（星期五）9:40-10：10

报  告  人：王学军 教授

工作单位：安徽大学

报告简介：The partially linear additive model is an exible and powerful model for evaluating the relationship between multivariate covariates and the response variable. The current paper considers the estimation problem of the model with additive measurement errors, along with some additional stochastic linear restrictions on the regression coefficients. We introduce a weighted corrected profile mixed estimator of the parametric component based on the corrected profile least squares approach and

weighted mixed regression method, and further establish the asymptotic normality of the proposed estimator. A Monte Carlo simulation experiment is conducted to illustrate theoretical results, and the findings from the simulation are satisfactory. Finally, we also apply the proposed procedure to analyze the Boston housing market data.

报告人简介：王学军，安徽大学理学博士、教授、博士生导师、大数据与统计学院副院长、统计学学科负责人。曾于2014年8月-2015年8月访问新加坡南洋理工大学数学系，2019年1月-2月访问香港浸会大学数学系。主要从事概率极限理论、统计大样本理论及其应用等方面的研究，近年来，在Bernoulli、中国科学等期刊上发表论文60余篇。主持国家自然科学基金项目4项、国家社科基金项目1项、安徽省杰出青年基金项目1项等。曾获安徽省科学技术奖三等奖2次、安徽省首届“青年数学奖”。担任SCI期刊《Journal of Nonparametric Statistics》、《Communications in Statistics-Theory and Methods》、《Communications in Statistics-Simulation and Computation》的副主编，兼任中国现场统计研究会生存分析分会副理事长、全国工业统计学教学研究会常务理事、中国现场统计研究会理事等。

报告五：Estimation and variable selection for high-dimensional spatial dynamic panel data models

报告华体会（中国）官方：2024年12月13日（星期五） 10:10-10：40

报  告  人：金百锁 教授

工作单位：中国科学技术大学

报告简介：Spatiotemporal modeling of networks is of great practical importance, with modern applications in epidemiology and social network analysis. Despite rapid methodological advances, how to effectively and efficiently estimate the parameters of spatial dynamic panel models remains a challenging problem. To tackle this problem, we construct consistent complex least-squares estimators by the eigen-decomposition of a spatial weight matrix method originally proposed for undirected networks. We no longer require all eigenvalues and eigenvectors to be real, which is a remarkable achievement as it implies that the proposed method is now applicable to spatiotemporal data modeling of directed networks. Under mild, interpretable conditions, we show that the proposed parameter estimators are consistent and asymptotically normally distributed. We also present a complex orthogonal greedy algorithm for variable selection and rigorously investigate its convergence properties. Moreover, we incorporate fixed effects into the spatial dynamic panel models and provide a model transformation so that the proposed method can also be applied to the transformed model. Extensive simulation studies and data examples demonstrate the effectiveness of the proposed method.

报告人简介：中国科学技术大学管理学院统计与金融系教授。研究方向：空间网络模型，变结构模型，随机矩阵。在PNAS，AoS，Biomerika，AAP，JoE等期刊发表学术论文60多篇。主持安徽省杰出青年基金项目和多项国家自然科学基金目。现为全国工业统计教学研究会理事，现场统计研究会教育统计与管理分会秘书长，现场统计研究会旅游大数据分会副理事长，《系统科学与复杂性英文版》编委等。