论文部分内容阅读
CRP(Constant Rebalancing Portfolios,即恒定再平衡投资组合)是一种重要的投资组合,它要求资产收益率序列必须满足独立同分布条件,这个限定条件影响了CRP在实际金融投资中的应用。为了使CRP发挥与其理论基础相称的实际效果,对真实金融数据进行基于序关系的重构,使得重构后的数据接近于满足独立同分布条件。在重构后的数据上构建最优CRP,这种策略称为rankCRP。证明了在适当的条件下rankCRP具有最优性。运用国际国内多个真实市场的大型历史数据进行检验,检验结果表明rankCRP在真实市场的表现优于CRP,远远超越市场指数,甚至战胜涨幅最大的证券。RankCRP在理论上的最优性表明,通过适当的重构,CRP也可以适用于非独立同分布收益率时间序列,拓宽了CRP理论的适用领域。RankCRP在实践上的有效性对金融投资实务有重要意义。
The Constant Rebalancing Portfolios (CRP) is an important investment portfolio. It requires that the sequence of return on assets must satisfy the independent and identically distributed condition, which restricts the application of CRP in actual financial investment. In order to make CRP play a practical effect commensurate with its theoretical foundation, the reorganization of the real financial data based on ordinal relation is made, so that the reconstructed data is close to satisfying the independent and identically distributed conditions. Build the optimal CRP on the reconstructed data. This strategy is called rankCRP. It is proved that rankCRP is optimal under appropriate conditions. Tests using large historical data from several real markets at home and abroad show that rankCRP performs better than CRP in real markets, far exceeding market indices and even overcoming the biggest gains. The theoretical optimality of RankCRP shows that CRP can also be applied to the time series of non-independent and same-rate returns with proper reconstruction, which broadens the application field of CRP theory. The practical effectiveness of RankCRP is of great importance to financial investment practice.