基于跟踪误差的指数化投资组合研究

发布时间：2018-05-08 16:23

本文选题：指数跟踪 + 动态调整　；参考：《东北大学》2012年硕士论文

【摘要】：指数化投资产生于20世纪70年代,经过近40年的发展,已经成为世界范围内的主要投资策略和投资方法之一。作为一种被动式的投资策略,指数化投资以复制和跟踪某一市场指数为目标,通过充分分散化投资组合来获取市场的平均收益率。它既没有积极基金管理的超额风险,也没有时机选择的限制,而且具有风险小、费用低、流动性高等优点,因此,探索指数化投资的投资模式及操作方法,对我国资本市场的发展具有重要的现实意义。本文围绕指数化投资这个主题,阐述了指数化投资的产生背景、指数化投资的优势及理论基础,并以跟踪误差为主线,介绍了跟踪误差的含义及计量跟踪误差的主要指标,然后通过最小化5种优化方法的跟踪误差,求得50只成分股票的最优权重,利用这5种优化组合进行了样本外的绩效检验,并对检验结果进行了比较。最后以平均绝对偏差模型为基础,根据投资者对跟踪误差和交易费用的不同偏好,建立了带比例交易费用的线性规划模型,在模型中考虑了预算限制、持仓限制等约束条件,并利用该模型对跟踪组合的定期调整问题和不定期调整问题进行了研究。主要结论如下。 (1)通过对5种优化方法构造的最优组合进行样本外绩效检验时,发现比较适合我国证券市场实际情况的指数优化模型是MAD模型。 (2)在对投资组合进行动态调整时,需要综合考虑交易费用、跟踪误差、调整频率等因素,并对这些因素进行平衡和协调。当对投资组合进行定期调整时,要综合考虑交易成本和跟踪误差两个因素,选择合适的调整时间间隔,使得目标函数最小化；在对投资组合进行不定期调整时,需要选择合适的调整阈值,对投资组合进行调整,以便得到较好的跟踪效果。
[Abstract]:Indexed investment emerged in the 1970s. After nearly 40 years of development, it has become one of the main investment strategies and methods in the world. As a passive investment strategy, the indexed investment aims at copying and tracking a market index, and obtains the average return rate of the market by fully diversifying the portfolio. It has neither the excess risk of active fund management nor the limitation of timing, but also has the advantages of low risk, low cost and high liquidity. Therefore, it explores the investment mode and operation method of indexed investment. The development of our country's capital market has important practical significance. Based on the subject of indexed investment, this paper expounds the background, advantages and theoretical basis of indexed investment, and introduces the meaning of tracking error and the main index of measuring tracking error, taking the tracking error as the main line. Then, by minimizing the tracking error of the five optimization methods, the optimal weights of 50 stocks are obtained, and the performance tests outside the samples are carried out using these five optimal combinations, and the results are compared. Finally, based on the average absolute deviation model, according to investors' different preferences for tracking error and transaction cost, a linear programming model with proportional transaction costs is established. The constraints such as budget constraints and position constraints are considered in the model. The model is used to study the periodic adjustment problem and the irregular adjustment problem of tracking combination. The main conclusions are as follows. 1) MAD model is the index optimization model which is more suitable for the actual situation of China's securities market when the performance of the optimal combination constructed by five optimization methods is tested outside the sample. 2) in the dynamic adjustment of the investment portfolio, the factors such as transaction cost, tracking error and adjusting frequency should be considered comprehensively, and these factors should be balanced and coordinated. When the portfolio is adjusted periodically, the transaction cost and tracking error should be considered synthetically, and the appropriate adjustment time interval should be chosen to minimize the objective function. It is necessary to select the appropriate adjustment threshold and adjust the portfolio to get better tracking effect.
【学位授予单位】：东北大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：F830.59;F224;F832.51

【参考文献】