A single-stage approach for cointegration-based pairs trading

Pairs trading can be regarded as conditional mean reversion strategies. The conditions are usually imposed in two stages: Identification of pairs' relationship and the opening (and closing) mechanism sequentially as a 'pass or fail' test. Nevertheless, as cointegration relationship is often not a 'yes or no' question but a 'strong or weak' one, dichotomizing the relationship through screening may not be optimal. This research presents a new single-stage approach to pairs trading based on a single 'power statistic'. Its superiority in attaining better risk-to-reward ratios is demonstrated empirically in a large scale backtest study.1