摘要：Based on the optimization of robust portfolio with tracking error, a robust mean-variance portfolio selection model of tracking error with transaction cost is presented for the case that only risky assets exist and expected returns of assets are uncertain and belong to a convex polyhedron. This paper aims to solve the problem of the portfolio with the selection of the ratio on the condition of maximumimum fluctuation of the tracking error, making the expectation of the return to be the maximumimum. It also makes the portfolio’s practical choice by the function of the linear transaction cost as the same time of construction and application of the model. Empirical analysis with five real stocks is performed by the method of LMI (Linear Matrix Inequality) to show the efficiency of the model.
