Directional bets on individual stocks bleed out in adverse markets regardless of how good the stock-picking is. A long-short portfolio calibrated to have zero sensitivity to broad market moves pins its fate instead on convergence: the bet is relative, not directional — that a mispriced spread between two related securities will narrow. This is the central insight of statistical arbitrage, and it starts with a clean decomposition of where stock returns come from.
This note derives the zero-beta long-short portfolio from CAPM, explains why market neutrality converts a directional view into a pure convergence bet, and positions the relative value idea within the anatomy of a quantitative trading system. The stationarity conditions that determine whether such a spread is actually tradeable are the subject of the next lesson.
Learning objectives. By the end of this note you should be able to:
- decompose a single-stock return into its market component and idiosyncratic residual using the CAPM single-factor model;
- construct a dollar-neutral long-short portfolio and verify that its beta is zero;
- explain why a zero-beta P&L earns or loses solely on spread convergence, not market direction;
- articulate the two competing explanations for the profitability of pairs trading — risk premium vs. temporary inefficiency — and state which the evidence favours;
- describe the five modules of a quantitative trading system and locate the relative value alpha within the alpha model.
In this lesson
-
- The CAPM decomposition of returns
-
- Zero-beta portfolios and market neutrality
-
- The spread as the object of the trade
-
- The relative value idea: what the edge is
-
- The anatomy of a quantitative trading system
Before you start
The full lesson, with worked examples and exercise solutions, is for members.
Read the full lessonNew to SelfMadeQuant.com? See membership options or browse the Statistical Arbitrage syllabus.