Detecting Lead-Lag Relationships in Stock Returns and Portfolio Strategies

Abstract

We propose a method to detect linear and nonlinear lead-lag relationships in stock returns. Our

approach uses pairwise Lévy-area and cross-correlation of returns to rank the assets from leaders to

followers. We use the rankings to construct a portfolio that longs or shorts the followers based on the

previous returns of the leaders, and every portfolio rebalance is based on a new ranking of leaders and

followers. The portfolio also takes an offsetting position on the SPY ETF so that the initial value of

the portfolio is zero. Our data spans from 1963 to 2022, and we use an average of over 500 stocks to

construct portfolios for each trading day. The annualized returns of our lead-lag portfolios are over

20%, and the returns outperform all lead-lag benchmarks in the literature. Only part of the lead-lag

relationships detected can be explained by those reported in the literature based on size, liquidity, analyst

coverage, or sector membership. Our findings support the slow information diffusion hypothesis; i.e.,

portfolios rebalanced once a day consistently outperform the bidiurnal, weekly, bi-weekly, tri-weekly,

and monthly rebalanced portfolios.

Keywords: Return prediction, Lead-lag relationships, Lévy-area, G12, G14, G17

JEL Classification: G11, G12, G14, G17