报告题目： Optimal Model Averaging Based on Forward-Validation

报 告 人： 张新雨研究员

时    间： 2020年10月30日下午3:00-4:00

地    点： 财经主楼806会议室

报告人简介：

张新雨，中科院数学与系统科学研究院/预测中心研究员。主要从事计量经济学和统计学的理论和应用研究工作，具体研究方向包括模型平均、机器学习和组合预测等。担任期刊《JSSC》领域主编、期刊《SADM》、《系统科学与数学》、《应用概率统计》等的AE或编委，是双法学会数据科学分会副理事长、国际统计学会当选会员和智源青年科学家。

报告摘要：

In this paper, noting that prediction of time series follows the temporal order of data, we propose a frequentist model averaging method based on forward-validation. Our method also considers the uncertainty of the window size in estimation, that is, we allow the sample size to vary in the candidate models. We establish the asymptotic optimality of our method in the sense of achieving the lowest possible squared prediction risk. We also prove that if there exist one or more correctly specified models, our method will automatically assign all the weights to them. The promising performance of our method for finite samples is demonstrated by simulations and an empirical example of predicting the equity premium.

经济与金融学院

2020年10月28日