主 题: 第30期学术午餐会——Graph-based two-sample tests
报告人: Jingru Zhang (Peking University)
时 间: 2018-04-24 12:00-13:30
地 点: Room 1560, Sciences Building No. 1
各位数院员工同学：
员工学术午餐会是在公司领导的大力支持下，由员工会负责组织的系列学术交流活动。午餐会每次邀请一位同学作为主讲人，面向全院各专业背景的员工介绍自己科研方向的基本问题、概念和方法，并汇报近期的研究成果和进展，是员工展示自我、促进交流的学术平台。
员工会已经举办了二十九期活动，我们将于2018年4月24日周二举办第三十期学术午餐会活动，欢迎感兴趣的老师和同学积极报名参加。
报告人简介：Jingru Zhang(张静茹) is a PhD student advised by Professors Weinan E and Wei Lin. Her research interests focus on high-dimensional statistics, computational statistics and big data analysis.
报告摘要[Abstract]：In the regime of two-sample comparison, tests based on a graph constructed on observations by utilizing similarity information among them is gaining attention due to their flexibility and good performances under various settings for high-dimensional data and non-Euclidean data. In this talk, we first review some existing graph-based tests for continuous data. Then we show that these tests could be problematic when there are repeated observations or ties in terms of the similarity graph. To address these problems, we study two ways to extend the existing graph-based tests. Analytic p-value approximations are also derived and shown to work well for finite samples, allowing the new tests to be fast applicable to large datasets. The new tests are illustrated in the analysis of a phone-call network dataset.
报名方式：请有意参加的老师在2018年4月23日（周一）中午12点前发送邮件至smsxueshu@126.com，我们将回复邮件和您确认，邮件报名方式仅限于老师，有意参加的同学请点击报名链接https://www.wjx.top/jq/22730468.aspx，谢谢！
