主题: Semiparametric Dynamic Portfolio Choice withMultiple Conditioning Variables
主讲人： Prof.Zudi Lu,University of Southampton
主持人：董朝华
时间：2015年12月25日, 上午10—11点
地点：格致楼 918会议室
主办单位：科研处 经济学院
主讲人简介：
Zudi Lu is a Professor/Chair in Statistics, in Mathematical Sciences Academic Unit and Southampton Statistical Sciences Research Institute (S3RI) at University of Southampton, UK. His research interest includes nonlinear financial time series modelling and financial statistics / econometrics; statistical inference & computation for nonlinear spatial/temporal modelling and prediction; applied temporal/spatial modelling for financial, environmental and socioeconomic risks; non-parametric/semi-parametric modelling and statistical learning.
主要内容：
Dynamic portfolio choice has been a central and essential objective forinvestors in active asset management. In this paper, we study the dynamicportfolio choice with multiple conditioning variables, where the dimensionof the conditioning variables can be either fixed or diverging to infinityat certain polynomial rate of the sample size. We propose a noveldata-driven method to estimate the optimal portfolio choice, motivated bythe model averaging marginal regression approach suggested by Li, Linton andLu (2015, Journal of Econometrics). More specifically, in order to avoid the curse of dimensionalityassociated with the multivariate nonparametric regression problem and tomake it practically implementable, we first estimate the marginal optimalportfolio choice by maximising the conditional utility function for eachunivariate conditioning variable, and then construct the joint dynamicoptimal portfolio through the weighted average of the marginal optimalportfolio across all the conditioning variables. Under some regularityconditions, we establish the large sample properties for the developedportfolio choice procedure. Both the simulation study and empiricalapplication well demonstrate the finite-sample performance of the proposedmethodology.
