【學術演講公告】113年3月5(二)

時  間:113年3月5日(星期二下午14:10~15:00)
地  點:管理學院新大樓M240
主講人:張瑄凌 教授(淡江大學 財務金融學系)
講  題:High Dimensional Markowitz Mean-Variance Optimization: Is Equal Weighted the Best Strategy?

Abstract
  Estimating and assessing the variance-covariance matrix (risk) of a large portfolio is an important topic both in financial econometrics and risk management. Ing and Lai (2011) proposed a novel technique, the Orthogonal Greedy Algorithm (OGA), with higher accuracy and less computational cost to deal with the estimation error in the high dimensional (large) matrix. In this paper, we adopt OGA on Markowitz minimum variance optimization by increasing the accuracy of the high dimensional matrix estimation to obtain the pure theoretical optimal and corresponding expected return. Here, p and n denote the number of stocks and that of historical data, respectively. First, we generate the simulated data, which mimics the theory distribution of financial return data, to compare the accuracy of the OGA and the thresholding method in Chen, Huang, and Pan (2015). The simulation result shows that the OGA has lower estimation error and higher stability than the thresholding method, especially at a great distance between p and n. Second, we randomly selected 100 (200, 300) stocks to form the portfolio as the investment target from 1980 to 2016. After assessing the portfolio's performance, the OGA method has a higher portfolio expected return and cumulated investment return than the naïve 1/N strategy.