报告题目： Spatial Weights Matrix Selection and Model Averaging for Spatial Autoregressive Models

主讲人：张新雨博士（中国科学院数学与系统科学研究院）

时间：2017年3月21日（周二）2:30 p.m. – 3:30 p.m.

地点：北院卓远楼305

主办单位：统计与数学学院

摘要：Spatial econometrics relies on spatial weights matrix to specify the cross sectional dependence; however, the candidate spatial weights matrix might not be unique. This paper proposes a model selection procedure to choose a weights matrix from several candidates by using a Mallows type criterion. We prove that when the true weights matrix is not in the candidates, the procedure is asymptotically optimal in the sense of minimizing the squared loss; otherwise, the procedure can select the true weights matrix consistently. We then propose a model averaging procedure to reduce the squared loss. We also provide procedures for the spatial model with heteroscadasticity and the model with both spatial lag and spatial error. Monte Carlo experiments show that proposed procedures have satisfactory finite sample performances. We apply the model selection and model averaging procedures to study the market integration in China using historical rice price.

报告人简介：张新雨，统计学博士（中科院），数学和系统科学研究所副研究员，优秀青年基金获得者，中科院优秀博士学位论文奖（2011）获得者，《系统科学与数学》期刊编委。主要研究领域为模型平均/选择，组合预测以及混合效应模型。在Annals of Statistics, Journal of the American Statistical Association, Biometrika, Journal of Econometrics等顶级统计学和计量经济学期刊发表过数十篇论文。
报告题目：A Two Stage Model of TV Viewers’ Strategic Viewing and Zapping Behavior
主讲人：石洋博士（中山大学岭南大学学院）

时间：2017年3月21日（周二）3:30 p.m. – 4:30 p.m.

地点：北院卓远楼305

主办单位：统计与数学学院

摘要：TVR (TV rating) is crucial for advertising prices. Most of previous literature has studied the zapping (channel switching) behavior for better measurement of TVR. To our knowledge, this is the first paper to explicitly model the impact of viewers’ strategic program viewing decision on their subsequent zapping behavior during commercial breaks. This is important especially when the program (e.g. drama) is continuously broadcast over a period: on one hand, viewers value the later episode more if they have viewed early episodes more (complementary consumption), and therefore are less likely to zap; on the other hand, previous viewing experience leads to more accurate expected valuation of latter episodes and concurrent programs of competing channels (learning), which could either increase or decrease zapping depending on the relative magnitude of the two expected values. This paper empirically models viewers’ dynamic program viewing decision and their subsequent zapping behavior in two stages. At a given time point, viewers decide whether to watch the piece of episode in stage one, and then decide whether to zap or not in stage two. In both stages, viewers make decisions based on their updated expectations of programs from past viewing experience.

报告人简介：石洋，哲学博士（香港科技大学），中山大学岭南大学学院助理教授，副研究员。主要研究领域为市场营销学模型和实证分析，在相关领域的工作获得过“中国营销科学博士生论坛优秀论文二等奖”。