概率统计系列讲座

时间：2019年12月26日，上午9:00-12:00，下午：15:00-18:00

地点：西南大学25教1802（学术报告厅）

报告一

报告题目：Semi-parametric inference for semi-varying coefficient panel data model with individual effects

报告人：胡雪梅教授（重庆工商大学数学与统计学院）

报告摘要：We study a semi-varying coefficient panel data model with unobserved individual effects, where all the covariates are high-dimensional variables. Based on multivariate local linear fitting, the transformation technique and the profile likelihood method，we establish semiparametric fixed effects estimators, semi-parametric random effects estimators, and their asymptotic properties. We also introduce a test for discriminating between a semi-varying coefficient random effects panel data model and a semi-varying coefficient fixed effects panel data model. The critical values are estimated by a bootstrap procedure. Monte Carlo studies exhibit the finite-sample performance of the proposed estimators and test statistics. Simulation results show that the methods perform well for moderate sample sizes. Finally, we analyze the cigarette consumption panel data from 46 American states covering the period 1963–1992.

报告人简介：胡雪梅，重庆工商大学数学与统计学院教授，长江上游经济中心博士生导师，中南大学理学博士，中国科学院数学与系统科学研究院控制论国家重点实验室系统科学博士后，伦敦政治经济学院国家公派访问学者，重庆市第五批优秀人才支持计划入选者和重庆市首届《统计学》研究生导师团队带头人。研究兴趣包括股价的趋势预测、高维数据分析、统计学习、半参数统计和随机过程的统计推断等。目前已在Journal of Multivariate Analysis、Journal of Nonparametric Statistic、Statistics & Probability Letters和Statistical Papers等国内外刊物发表论文30多篇，其中SCI收录22篇；2020年在《高等教育出版社》出版专著《高维统计模型的估计理论与模型识别》1部。现主持或完成国家自然科学基金青年项目1项、教育部人文社科青年项目1项、重庆市科委项目4项和市教委科技项目2项；参与完成973和国家社科等项目8项；参与获得重庆市科学技术奖二等奖1项。

报告二

报告题目：QR Decomposition based Orthogonality Statistical Inferences for Semiparametric Regression Models

报告人：赵培信教授（重庆工商大学）

报告摘要：We study the estimation for a class of semiparametric regression models, such as the partially linear models and varying-coefficient partially linear models with longitudinal data. By combing quadratic inference functions with QR decomposition technology, we propose a new estimation method for the parametric and nonparametric components. The resulting estimators for parametric and nonparametric components do not affect each other, and then it is easy for application in practice. Under some mild conditions, we establish some asymptotic properties of the resulting estimators. Some simulation studies are undertaken to assess the finite sample performance of the proposed estimation procedure.

报告人简介：赵培信，博士，教授，重庆工商大学硕士生导师。近几年来一直从事非参数统计以及复杂数据处理方法的研究。作为项目负责人先后主持了国家自然科学基金青年基金项目1项、国家社会科学基金一般项目1项以及重庆市前沿与应用基础研究计划一般项目1项等课题的研究工作，并且参与各类科研项目多项。在国内外重要刊物发表专业学术论文40余篇，SCI收录20余篇。

报告三

报告题目：Doubly robust kernel smoothing density estimation when group membership is missing at random

报告人：唐万副教授（美国杜兰大学公共卫生学院）

报告摘要:The density function is a fundamental concept in data analysis. When a population consists of heterogeneous subjects, it is often of great interest to estimate the density functions of the subpopulations. Nonparametric methods such as kernel smoothing estimates may be applied to each subpopulation to estimate the density functions if there are no missing values. In situations where the membership for a subpopulation is missing, kernel smoothing estimates using only subjects with membership available are valid only under missing complete at random (MCAR). In this talk, I will present a doubly robust kernel smoothing methods for density function estimates by combining models of the missing mechanism and prediction models of the membership under the missing at random (MAR) assumption. The asymptotic properties of the new estimates are developed, and simulation studies and a real study in mental health are used to illustrate the performance of the new estimates.

报告人简介：唐万，1992年毕业于西南师范大学数学系，1995年获北京大学硕士学位(导师:丁石孙教授)，2004年获美国罗切斯特大学博士学位(导师: Allan Greenleaf教授)，现为美国杜兰大学副教授，西南大学客座教授。研究兴趣包括纵向数据以及有数据缺失情形的统计推断，非参数光滑模型，因果推断等及其在生物医学特别是精神病学和行为科学方面的应用。目前在国际重要上发表论文70余篇，其中在Statistical Methods in Medical Research、Journal of Statistical Planning and Inference、Biometrics，Journal of Nonparametric Statistic、Statistics in Medicine和Journal of Functional Analysis等数学及统计杂志发表论文30余篇，在The American Journal of Psychiatry和Nursing Research等医学杂志发表论文40余篇；主持完成美国NIH的R21和R33项目2项、合作完成数十项美国NIH及其它机构资助的项目。在著名的CHAPMAN & HALL/CRC统计学教材系列合著出版研究生教材一部(Applied Categorical and Count Data Analysis)。

报告四

报告题目: A new method for solving some first passage time problems by Laguerre series expansion

报告人：张志民教授（重庆大学）

报告摘要:We propose for the first time an explicit closed-form Laguerre series expansion formula for the first passage time density function of a general jump diffusion. In contrast to existing methods in the literature based on numerical Laplace transform inversion, the proposed formula enjoys several advantages: it is in analytical closed-form, simple to implement, and converge quickly. Two methods are proposed to compute the Laguerre coefficients, where the first method is based on the fluid embedding technique, and the second method relies on potential densities. Various numerical examples are presented to show effectiveness of our method.

报告人简介：张志民，重庆大学教授，博士生导师，重庆市学术技术带头人，主要研究方向包括风险管理与精算学、金融数学、金融统计、应用随机过程等。目前已经发表50余篇SCI论文，其中多篇论文发表在精算学主流杂志IME、SAJ、ASTIN上。作为项目负责人，主持国家自然基金面上项目2项，青年基金1项，重庆市科委面上项目2项，教育部博士点基金1项。

报告五

报告题目：Single-pass randomized algorithms for LU decomposition

报告人：李寒宇教授（重庆大学）

报告摘要：In this talk, we will introduce some single-pass randomized algorithms to compute LU decomposition. These algorithms need only one pass over the original matrix and hence are very suitable for extremely large and high-dimensional matrix stored outside of core memory or generated in a streaming fashion. Rigorous error bounds and complexity of these algorithms are provided. Numerical experiments show that these single-pass algorithms have the similar accuracy and runtime (excluding the cost of matrix transfer) compared with the state-of-the-art randomized algorithms for LU decomposition.

报告人简介：李寒宇，博士、重庆大学教授、博士生导师，现任重庆工业与应用数学学会副理事长。主要研究方向：随机数值代数、统计计算等。先后主持国家自然科学基金项目2项、重庆市自然科学基金项目2项，在国际知名杂志，如：SIAM Journal on Matrix Analysis and Applications, Numerical Linear Algebra with Applications、Linear Algebra and its Applications等发表学术论文多篇。

更多信息见http://math.unicorn365.cn/staff/detail?userId=269

报告六

报告题目：Measuring Tail Operational Risk in Univariate and Multivariate Models under Extreme Losses

报告人：杨洋教授（南京审计大学统计与数学学院）

报告摘要：This paper considers some univariate and multivariate operational risk models, in which the loss severities are modelled by some weakly dependent and heavy-tailed positive random variables, and the loss frequency processes are some general counting processes. In such models, we derive some limit behavior for the Value-at-Risk and Conditional Tail Expectation of aggregate operational risks. The methodology is based on capital approximation within the framework of the Basel II/III regulatory capital accords, which is the so-called Loss Distribution Approach. We also conduct some simulation studies to check the accuracy of our obtained approximations and the (in)sensitivity due to different dependence structures or the heavy-tailedness of the severities.

报告人简介：杨洋，博士，教授，现任南京审计大学统计与数学学院副院长。长期从事金融统计、保险精算、风险管理、应用概率论等研究工作。先后主持国家自然科学基金2项、教育部人文社会科学基金1项、江苏省自然科学基金面上项目3项、中国博士后科学基金特别资助项目1项和面上项目2项、江苏省优秀科技创新团队项目1项、江苏省高校自然科学基金重大项目2项。先后访问美国University of Iowa、香港大学和立陶宛Vilnius University。2010年以来，累计发表学术论文83篇，其中66篇被SCI检索、14篇被SSCI检索(第一或通讯作者50篇)，由科学出版社出版学术专著2部，包括《European Journal of Operational Research》、《Stochastic Processes and their Applications》、《Insurance: Mathematics and Economics》、《Scandinavian Actuarial Journal》、《European Actuarial Journal》、《Extremes》、《Journal of Applied Probability》、《Journal of Computational and Applied Mathematics》、《中国科学》等。曾获得浙江省自然科学奖三等奖1项、江苏省统计科研优秀成果奖二等奖1项、三等奖2项、江苏省工业与应用数学奖青年奖。曾获得江苏省“333工程”中青年学术技术带头人、江苏省“六大人才高峰”高层次人才、江苏高校“青蓝工程”中青年学术带头人、江苏高校“青蓝工程”优秀青年骨干教师、江苏省“数学”重点建设学科负责人、江苏省“统计学”重点建设学科方向负责人等荣誉称号。现任江苏省概率统计学会副理事长、中国工程概率统计学会常务理事、全国工业统计学教学研究会理事、江苏省工业与应用数学学会理事。