Home / Ideas / Johansen Triplet Stat-Arb

Pairs trading & cointegration (ETFs) · 2026-08-31

Johansen Triplet Stat-Arb

trade the mean-reverting eigenvector spread of a three-ETF basket

expected Sharpe 0.4–0.9confidence: low-to-mediumfree daily data

The Johansen procedure tests three or more ETFs jointly and returns a stationary cointegrating vector even when no clean two-leg pair exists; trading the eigenvector-weighted basket spread is a multivariate mechanic distinct from two-leg pairs and from PCA factor hedging (Johansen maximizes cointegration, PCA maximizes variance).

Universe

Economically coherent ETF triplets, e.g. XLE/XOP/OIH (energy), GLD/GDX/GDXJ (gold complex), TLT/IEF/LQD (rates/credit), EWG/EWQ/EWL (core Europe) — daily closes.

How it works

Run Johansen on a 250-day window; if a significant cointegrating vector exists, form the eigenvector-weighted portfolio, compute its half-life and z-score, enter beyond ±1.5, exit near 0, re-estimate weights on rolling refit, cap holding at ~2× half-life.

Expected performance

Research-derived Sharpe estimate: 0.4–0.9. in-sample cointegration frequently fails out-of-sample due to low test power — the dominant risk here).

Backtest this idea with SignalChain

This is a research lead — not a finished backtest. SignalChain takes an idea like this and runs the whole pipeline inside Claude Code: it researches the concept against academic and practitioner sources, sets benchmarks, writes and lints a VectorBT backtest, runs it, and grades the result PASS/FAIL. One command:

/signalchain Johansen multivariate cointegration stat-arb on three-ETF baskets, trade eigenvector-weighted spread z-score with rolling refit and half-life holding cap Get SignalChain — $49 →

Research & sources

Not financial advice. This page describes a research idea, not a recommendation. Any performance figures are hypothetical, research-derived estimates and are not indicative of future results. SignalChain is a research and educational tool; you are solely responsible for any decisions you make.