主 题：A Statistical Model for Social Network Labelin
主讲人：王汉生教授
主持人：林华珍教授
时 间：2014年5月7日上午10:30-11:30
地 点：通博楼B座212学术会议室
主办单位：统计学院 统计研究中心 科研处
主讲人简介：
北京大学光华管理学院商务统计与经济计量系,嘉茂荣聘教授，博导，系主任。北京大学商务智能研究中心、主任。博雅立方科技有限公司首席科学家。微信公众号“狗熊会”创始人。1998年北京大学数学学院概率统计系本科毕业，2001年美国威斯康星大学麦迪逊分校统计系博士毕业。2003年加入光华至今。国内外各种专业杂志上发表文章七十余篇，并（合）著有中英文专著各一本。国际统计协会、英国皇家统计协会、美国统计协会、美国数理统计协会、泛华国际统计协会的会员。先后历任以下国际学术刊物副主编（Associate Editor）：The Annals of Statistics (2008—2009), Computational Statistics & Data Analysis (2008—2012)，Statistics and its Interface (2010—现在), Journal of the American Statistical Association (2011—现在)，以及Statistica Sinica (2011—现在)。Journal of Business and Economics Statistics (2012—现在), Science China: Mathematics (2013—现在）
内容提要：
We consider here a social network from which one observes not only network structure (i.e., nodes and edges) but also a set of labels (or tags, keywords) for each node (or use These labels are self-created and closely related to the user's career status, life style, personal interests, and many others.Thus, they are of great interest for online marketing.To model their joint behavior with network structure, a statistical model is developed.The model is based on the classical $p_1$ model but allows the reciprocation parameter to be label dependent. For both dense and sparse networks, we obtain maximum likelihood estimators, which are statistically efficient but computationally expensive. To alleviate the computational cost, a novel conditional maximum likelihood estimator is proposed for large scaled sparse network. The asymptotic properties of these estimators are investigated.Simulation studies are conducted and a real Sina Weibo dataset is analyzed.
