主 题:非参数条件分布的对称性检验
主讲人: 北大光华管理学院 宋晓军博士
主持人:经济与管理研究院 郭萌萌 副教授
时 间:2014年10月24日下午2:30点—4:00点
地 点:柳林校区颐德楼H515
主办单位:经济与管理研究院 科研处
主讲人简介:
宋晓军,北京大学光华管理学院助理教授,于2014年获得Universidad Carlos III de Madrid, Spain 的经济学博士学位, 曾先后获得经济学和金融学等三个硕士学位。主要研究领域包括计量理论,半参数和非参数估计方法,模型设定检验等。目前已经有一篇独立作者的论文在国际顶级期刊Journal of Econometrics 修改,其他工作论文也都投向国际其他顶级期刊。
内容提要:
This article proposes tests of symmetry of conditional distributions around a nonparametric location function able to detect general non-parametric alternatives. The test is developed in a general serial dependence context, where innovations may exhibit an unknown higher order serial dependence structure. The test statistic is a functional of the joint empirical distribution of non-parametric residuals and explanatory variables, which can detect non-parametric alternatives converging to the null at the parametric rate \sqrt(n). Critical values are estimated with the assistance of a bootstrap technique easy to implement, and the validity of the resulting test is formally justified under the regularity conditions. A Monte Carlo study examines the finite sample properties of the test. We also investigate whether losses are more likely than gains given the available information in stock markets using our testing approach.