Pairs Trading: Performance of Markov Regime-Switching Model with Mean Reversion-Evidence in S&P 500 Stock Market

碩士 === 國立高雄應用科技大學 === 金融資訊研究所 === 101 === There is a lack of literature on the pair trading model which can catch both the mean-reverting and two different states of spreads. The purpose of this study is to determine if the use of the model which combines the Markov regime-switching model and the Va...

Full description

Bibliographic Details
Main Authors: Shu-Yu Tsai, 蔡淑瑜
Other Authors: Chia-Chien Chang
Format: Others
Language:en_US
Published: 2013
Online Access:http://ndltd.ncl.edu.tw/handle/y8k83n
Description
Summary:碩士 === 國立高雄應用科技大學 === 金融資訊研究所 === 101 === There is a lack of literature on the pair trading model which can catch both the mean-reverting and two different states of spreads. The purpose of this study is to determine if the use of the model which combines the Markov regime-switching model and the Vasicek model would make a higher profit. This paper uses stocks in the S&P 500 Index from 2006/1/1 to 2012/09/28 to conduct an empirical study on the performance of pairs-trading strategy. We choose the smallest sum of squared differences of pairs to form a portfolio by calculating the smallest sum of squared differences in the normalized prices of each pair. Finally, we will compare the performance of the different portfolio and the different trading period respectively. The empirical results show that the trading rule of the Markov regime-switching model and the Vasicek model have the best performance in a simple portfolio, and it is found that the shorter trading period, the higher performance. Therefore, the trading rule of the Markov regime-switching model and the Vasicek model has the practicability to the investors who try to get good profits by pairs-trading and have little capital.