Cointegration and Relative Value Arbitrage

42 Pages Posted: 29 May 2016 Last revised: 19 Aug 2016

See all articles by Binh Huu Do

Binh Huu Do

Monash University; Financial Research Network (FIRN)

Robert W. Faff

University of Queensland

Multiple version iconThere are 2 versions of this paper

Date Written: August 19, 2016


This paper examines a new method of identifying close economic substitutes in the context of relative value arbitrage. We show that close economic substitutes correspond to a special case of cointegration whereby individual prices have approximately the same exposure to a common stochastic factor, or the cointegrating relation is approximately one-to-one. Empirical analysis of cointegration-based pairs trading shows that a metric of closeness constructed from the cointegrating relation strongly predicts the probability of convergence and profitability of pairs trades. Over period 1962-2013, a strategy that trades cointegrated pairs of near-parity generates average returns of 58 bps per month after trading costs, experiences 71% probability of convergence and outperform pairs that are selected using the conventional method of minimizing price distance. When extending to triplets trading, the predictability of the metric of closeness remains, however trading of cointegrated baskets of three stocks is less profitable due to smaller mispricings.

Keywords: Relative value arbitrage, convergence trading, statistical arbitrage, pairs trading, cointegration, Law of One Price

JEL Classification: G11, G12, G14

Suggested Citation

Do, Binh Huu and Faff, Robert W., Cointegration and Relative Value Arbitrage (August 19, 2016). Available at SSRN: or

Binh Huu Do (Contact Author)

Monash University ( email )

Building 11E
Clayton, Victoria 3800

Financial Research Network (FIRN)

C/- University of Queensland Business School
St Lucia, 4071 Brisbane


Robert W. Faff

University of Queensland ( email )

St Lucia
Brisbane, Queensland 4072

Register to save articles to
your library


Paper statistics

Abstract Views
PlumX Metrics