Home / Ideas / t-Statistic Trend Strength

Cross-Sectional Momentum & Trend-Following · 2026-09-12

t-Statistic Trend Strength

rank by how *reliable* the trend is, not how big the return is

expected Sharpe 0.6–1.0confidence: mediumfree daily data

Ranking assets by the t-statistic of an OLS log-price slope (trend consistency) instead of raw return favors steady trends over lucky spikes; recent work on a century of industry trends reports t-stat-based trend estimation cut portfolio turnover ~66% while preserving edge, directly attacking the transaction-cost failure mode. Distinct from residual momentum (regression *residual return*) — here the signal is the *slope significance* of the asset's own price.

Universe

12 liquid multi-asset ETFs (SPY, QQQ, IWM, EFA, EEM, TLT, IEF, GLD, DBC, VNQ, HYG, LQD).

How it works

each month regress log price on time over 126 days, rank by slope t-stat, long the top positive-and-significant names equal-weight, hold monthly (low turnover from the smoothed signal).

Expected performance

Research-derived Sharpe estimate: 0.6–1.0.

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 Rank 12 multi-asset ETFs by t-statistic of 126-day log-price trend slope, hold top positive-trend names, monthly rebalance 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.