均值收斂交易策略在金融市場上一直以來都被廣泛的應用，而均值收斂交易策略在配對交易下的表現往往較單一商品佳。然而，均值收斂模型假設分佈為常態分配，但股票報酬分佈一直以來存在厚尾的問題，而Student's t 分佈擁有厚尾的特性。本文藉由均值收斂模型假設分佈為Student's t 分佈下可較佳捕捉厚尾的性質，且利用台灣金融市場的交易資料進行回測，並將其結果與均值收斂模型在常態模型下進行比較。

The mean reverting trading strategy has been widely used in the financial market, and the pair trading performance of the mean reverting strategy is often better than a single commodity. However, in empirical studies, we obtain that the density of log returns, but the density of log return usually has fat-tailed problem. The Student's t distribution has the characteristic of fat tail. In this paper, we propose the reverting model under the Student's t distribution can capture better fat-tailed property, and use stock data from Taiwan finance market. We show the empirical results in order to compare the performance of two reverting model.

[1] Timofei Bogomolov. Pairs trading based on statistical variability of the spread process.
Quantitative Finance, 13(9):1411–1430, 2013.
[2] Rama Cont. Empirical properties of asset returns: stylized facts and statistical issues.
2001.
[3] Bo Liu, Lo-Bin Chang, and Hélyette Geman. Intraday pairs trading strategies on high
frequency data: The case of oil companies. Quantitative Finance, 17(1):87–100, 2017.
[4] Chuanhai Liu and Donald B Rubin. Ml estimation of the t distribution using em and
its extensions, ecm and ecme. Statistica Sinica, pages 19–39, 1995.
[5] Thorben Lubnau and Neda Todorova. Trading on mean-reversion in energy futures
markets. Energy Economics, 51:312–319, 2015.
[6] Johannes Stübinger and Sylvia Endres. Pairs trading with a mean-reverting jump–
diffusion model on high-frequency data. Quantitative Finance, pages 1–17, 2018.
[7] Wing-Keung Wong, Meher Manzur, and Boon-Kiat Chew. How rewarding is technical
analysis? evidence from singapore stock market. Applied Financial Economics, 13(7):
543–551, 2003.