5 articles
On SPY from 1994 to November 2026, neither a 200-day trend rule (9.4% a year) nor a 2-day RSI mean-reversion rule (7.0%) beat buy-and-hold (10.8%), and both roughly halved the worst fall. The trend rule won 44% of its trades and lagged in most years; the reversion rule won 69% and lost 25% in five weeks in 2020.
Four errors, each measured on the same data: look-ahead turned a 200-day moving-average rule from 9.4% a year into 20.9%; today's S&P 500 members beat the real equal-weight fund by 6.3 points a year since 2004; 10 bp a trade sank a 45-trade-a-year rule; and the best of 355 moving-average pairs ranked 322nd out of sample.
From 1927 to September 2026, the tenth of US stocks with the best past year returned 16.9% a year before costs, against 10.3% for the market. Winners minus losers earned 7.4% a year, but lost 74% in July–August 1932, 58% in 2008–09, and has not regained its November 2008 peak.
From July 1927 to September 2026 the highest-yielding 30% of US stocks compounded at 11.34% a year against 10.26% for the market. Most of that edge is the value premium: after size and value, 0.21 points a year are left. The top 10% by yield did worse than the next two groups, with more risk.
The Sharpe ratio divides an investment's return above the risk-free rate by the standard deviation of those returns, measuring reward per unit of volatility. Above 1 is generally considered good. A very high figure often signals hidden tail risk rather than skill, because volatility and risk are not the same thing.
