题 目：DOUBLE CROSS VALIDATION FOR THE NUMBER OF FACTORS IN APPROXIMATE FACTOR MODELS
时 间：2020年7月11日(周六)上午10:30-11:30
地 点：Zoom会议ID：615 3970 4192
题 目：DOUBLE CROSS VALIDATION FOR THE NUMBER OF FACTORS IN APPROXIMATE FACTOR MODELS
主讲人：夏应存教授 新加坡国立大学统计与应用概率系
摘 要：In this paper, we propose an efficient cross validation (CV) method to determine the number of factors in approximate factor models. The method applies CV twice, first along the directions of observations and then variables, and hence is referred to hereafter as double cross-validation (DCV). Unlike most CV methods, which are prone to over-fitting, DCV is statistically consistent in determining the number of factors when both dimension of variables and sample size are sufficiently large. Simulation studies show that DCV has decent performance in comparison to existing methods in selecting the number of factors, especially when the idiosyncratic error has heteroscedasticity, or heavy tail, or relatively large variance.
报告人简介：
夏应存，2000年毕业于香港大学统计系，现任新加坡国立大学统计与应用概率系教授。研究兴趣包括时间序列分析、半参数方法及降维、传染病的统计建模等。在PNAS, American Naturalist, Annals of Statistics, JRSSB, JASA, Biometrika, JOE等期刊上发表多篇论文， 研究成果曾被Nature News等十几家学术媒体报道。现任Annals of Statistics 副主编(AE)。
