Pairs trading and statistical arbitrage
Two securities that normally move similarly are traded once they diverge, in expectation that the gap will close again. Historically well documented, with a clearly documented decline in profitability since the early 2000s.
In pairs trading, you look for two securities that normally move very similarly, say two companies from the same industry. When they diverge unusually far, you buy the relatively cheaper one and short the relatively more expensive one, expecting the gap to close again.
The foundational study on this comes from economists Evan Gatev, William Goetzmann, and Geert Rouwenhorst. They tested the strategy with daily price data from 1962 to 2002 and found a clear annual excess return for the best pairs, one that held up even after accounting for conservatively estimated trading costs.
The decisive point for context is how it developed over time. The same authors already documented that profitability weakened in the final years of their study period. Later studies with data through 2009 found a further clear decline, partly because more and more capital flowed into similar strategies, making the divergences smaller and shorter.
This is a textbook example of a pattern that recurs across several strategy types: an effect gets found, published, used by more and more professional players, and weakens itself as a result. What was a reliable income source in the 1960s is today a fiercely contested field among specialized hedge funds with very fast execution.
Gatev, Goetzmann, and Rouwenhorst (2006) formed pairs by minimum distance of normalized historical prices and found annualized excess returns of roughly eleven percent for the twenty best pairs over the full 1962 to 2002 study period, testing both immediate and one-day-delayed execution to rule out data-snooping effects.
Do and Faff (2010, 2012) replicated the methodology on US stocks through 2009 and documented a further clear decline in profitability compared to the original study period, attributing it largely to a growing share of non-converging pairs. Zhu (2024), replicating with data from the last twenty years, still finds positive but, relative to the original period, smaller excess returns, and identifies the default spread among other things as an explanatory factor, suggesting compensation for risk rather than pure market inefficiency.
Economically, the strategy is classified as a form of statistical arbitrage, exploiting the divergence of two closely related securities without either position needing to be over- or undervalued in an absolute sense. Gatev et al. themselves note that the documented decline in returns coincides in timing with a massive inflow of capital into related, market-neutral hedge fund strategies, supporting the explanation that growing competition shrinks the opportunities themselves.
Summary
- Pairs trading bets on two closely related securities returning to their usual gap.
- The original study found clear excess returns over forty years through 2002.
- Later studies show a clear decline, likely from growing competition.
Did you get it?
What is the basic idea of pairs trading?
Trading two closely related securities once they diverge unusually far, expecting a return to their usual gap.
What did Gatev, Goetzmann, and Rouwenhorst find for 1962 to 2002?
For the best pairs, annualized excess returns of roughly eleven percent, even after conservatively estimated trading costs.
What do Do and Faff largely attribute the post-2002 decline in profitability to?
A growing share of non-converging pairs.
Sources and further reading
- Gatev, E., Goetzmann, W. N. and Rouwenhorst, K. G. (2006), Pairs Trading: Performance of a Relative-Value Arbitrage Rule, Review of Financial Studies View source ↗
- Do, B. and Faff, R. (2010), Does Simple Pairs Trading Still Work?, Financial Analysts Journal
Related
- Strategy types overviewStrategy Types
- Momentum and trend followingStrategy Types
- Compound interestStage 0