基于因子模型的指数跟踪及实证分析

Factor Model Based Index Tracking and Empirical Analysis

指数跟踪是指数基金和机构投资者广泛使用的被动投资管理策略.通过建立股票收益的多因子模型,提出了将组合的贝塔值控制在合适范围内,并在期望超额收益非负的条件下,最小化组合风险的指数跟踪模型.同时,考虑到实际需要,在模型中限制了组合中股票的数量和持有量.实证分析结果表明,通过选取不同的控制参数,该模型产生的跟踪组合既能实现较小的跟踪误差,也能实现一定的超额收益.

Index tracking is a popular passive investment strategy widely used by index funds and institutional investors. In this paper, we present a cardinality constrained index tracking model based on factor model. The model minimizes the variance of the portfolio with constraints on factor betas and expectes excess return. Taking into account the practical investment management, we also consider restrictions on the total number of stocks selected. The result of empirical analysis suggests that, by choosing different parameters, the optimal portfolios of our model can achieve low tracking error and excess return.