Pairs trading : a copula approach

• Main Authors: Liew, Rong Qi, Wu, Yuan
• Other Authors: Nanyang Business School
• Format: Article
• Language: English
• Published: 2013
• Subjects: DRNTU::Business::Finance::Funds
• Online Access: https://hdl.handle.net/10356/98349; http://hdl.handle.net/10220/17826
• Institution: Nanyang Technological University

Pairs trading is a technique that is widely practiced in the financial industry. Its relevance has been constantly tested with updated samples, and its profitability is acknowledged among practitioners and academics. Yet in pairs trading, the notion of correlation is central, and the use of correlation or cointegration as a measure of dependency is ultimately its Achilles' heel. To overcome this limitation, this article employs the use of copulas, which is much more realistic and robust, to develop trading rules for pairs trading. Copulas are useful extensions and generalizations of approaches for modeling joint distributions and dependence between financial assets. A trading strategy that involves the use of copulas has been compared against two most commonly applied conventional strategies. The empirical results suggest that the proposed strategy is a potentially powerful analytical alternative to the traditional pairs trading techniques.