统计学系系列讲座之348-349期

统计学系系列讲座之348期

时　间：2019年6月27日（星期四）10:30-11:30

地　点：思源教授楼726室

主持人：沈娟 副教授 复旦大学管理学院统计学系

主　题：Network Response Regression for Modeling Population of Networks with Covariates

主讲人：Prof. Emma Jingfei Zhang　Miami University

简　介：

Prof. Zhang is an Assistant Professor in the Department of Management Science at the Miami Business School of the University of Miami. Her research interest involves the statistical analysis of network data, which includes multiple network inference, network community detection and network sampling. She is also interested in point processes and their applications.

摘　要：

Multiple-subject network data are fast emerging in recent years, where a separate network over a common set of nodes is measured for each individual subject, along with rich subject covariates information. Existing network analysis methods have primarily focused on modeling a single network, and are not directly applicable to multiple-subject networks with subject covariates. In this talk, we introduce a new network response model, where the observed networks are treated as matrix-valued responses, and the individual covariates as predictors. The new model characterizes the population-level connectivity pattern through a low-rank intercept matrix, and the parsimonious effects of subject covariates on the network through a sparse slope tensor. We formulate the parameter estimation as a non-convex optimization problem, and develop an efficient alternating gradient descent algorithm. We establish the non-asymptotic error bound for the actual estimator from our optimization algorithm. Built upon this error bound, we derive the strong consistency for network community recovery, as well as the edge selection consistency. We demonstrate the efficacy of our method through two brain connectivity studies.

统计学系系列讲座之349期

时　间：2019年7月4日（星期四）16:00-17:00

地　点：史带楼302室

主持人：朱仲义 教授 复旦大学管理学院统计学系

主　题：Missing Data and Measurement Error: Estimation of Pathways of Productivity Loss of Injured Workers

主讲人：Professor Depeng Jiang　University of Manitoba, Winnipeg, Canada

简　介：

蒋德鹏教授于2002年获东南大学管理科学与工程学博士学位，先后赴美国霍普金斯大学、加拿大约克大学进行博士后研究。现为加拿大曼尼托巴大学公共卫生学系终身教授，从事生物统计学的教学和科研工作，兼任曼尼托巴大学统计咨询中心主任。同时，他还是东南大学、吉林大学和南京林业大学等多所高校的客座教授。蒋教授在生物统计领域有较深的造诣，对大数据建模、纵向数据分析和混合统计模型有着特别的兴趣和深入的研究。多年来蒋教授为来自许多学科的研究者提供统计咨询，指导硕士和博士研究生，积累了丰富的统计咨询经验。目前已发表论文七十余篇。
 

摘　要：

The presentation serves as an illustration of the impact of missing data and measurement error on estimation of the course of recovery for injured workers for shoulder and elbow disorders. It is important to look at changes in work-related outcomes for the injured workers, such as the likelihood of returning to work, any work accommodations needed to allow workers to remain at work, as well as any disability or loss in productivity that was experienced while at work.  Assessment of these outcomes and prognostic factors may face challenging of missing data and measurement errors. We proposed latent class and growth mixture model approach to deal with the missing data and measurement problems. We will show how the new approaches can overcome the problems of current available statistical methods and help to identify the distinct trajectories of worker productivity loss and the associated prognostic factors.

 统计学系 

2019-6-24