Finance-Insurance
Time: 11.00 am
Date:03th of July  2025
Room 3001

Paolo ZAFFARONI (Imperial College Business School) “STATISTICAL ARBITRAGE WITHOUT ARBITRAGE”

Abstract : Statistical arbitrage strategies are quantitative trading strategies based on alpha, i.e., on the signal extracted from the residuals when fitting an asset pricing model to re- turns data. We develop a normative theory that combines the insights of mean-variance portfolio choice with statistical arbitrage in the no-arbitrage setting of the APT, that is we study statistical arbitrage without arbitrage . We establish a novel two-fund separation result that combines the inefficient statistical arbitrage portfolio and beta portfolio (i.e., the portfolio stemming from factor asset pricing models), showing how their combination can span the efficient frontier. In general, as the number of assets increases, the “statistical arbitrage portfolio” dominates the “beta portfolio” both in terms of the magnitude of its weights and in terms of its SR. Exploiting some insights of mean-variance portfolio choice, we show how to construct a special statistical arbitrage portfolio that does not require estimating alpha, in contrast to the common view. When statistical arbitrage is combined with factor asset pricing modelling, alpha and the factors’ risk premia might not be jointly identified, jeopardizing the possibility to construct a statistical arbitrage portfolio. We derive a penalized estimator under a no-arbitrage constraint that allows for the econometric identification of the statistical arbitrage portfolio, leading to a shrinkage-type estimator. We demonstrate our theoretical insights by means of Monte Carlo experiments and empirical applications.

[joint work with Massimo Dello Preite and Valentina Raponi]

Organizers:  Zakoian Jean-Michel