关键词: 投资组合选择, 变动基数, 系统误差-估计误差权衡, 尾部风险

Abstract: The systematic error and estimation error in the choice of portfolios are important factors that determine the out-of-sample performance, but its tradeoff is affected by the asset cardinality N. In this paper, under the setting of the variable cardinality, the method of Bootstrapping and out-of-sample rolling are applied to the test of the equally weighted, the minimum variance portfolio and its error correction strategy performance and tail risk. The findings are as follows: (1)There is an inverted U-shaped relationship between the difference between the minimum variance portfolio and the equally weighted strategy in the out-of-sample period and N. (2)The tail risk of the minimum variance portfolio decreases rapidly with the expansion of N. Overall, the tail risk of the minimum variance portfolio is lower than the equally weighted strategy. (3)There is a positive correlation between the turnover rate of the minimum variance portfolioand N, and blindly increasing the cardinality will bring unnecessary losses. The research results show that investors should choose the asset cardinality rationally according to the length of the estimation window, and make full use of the diversification benefits brought by the minimum variance portfolio.

Key words: portfolio selection, variable cardinality, systematic-estimation error trade-off, tail risk