Newfound Research explores whether prolonged underperformance in factor investing truly signals failure or just statistical noise. Using Bayesian analysis, it argues even a decade-long slump like value’s ~25% drawdown since 2006 may not be enough to invalidate a factor, challenging how investors interpret weak performance.
Factor Fimbulwinter
Newfound Research
Corey Hoffstein
Research
12 Pages
Key Takeaways
Value Drawdown Context: Price-to-book has remained ~25% below its 2006 peak despite 10+ years of underperformance, highlighting how long factor slumps can persist without definitive invalidation.
Evidence Threshold Problem: Simulations suggest it could take multiple decades or even full careers of weak returns before statistically rejecting a factor with high confidence.
Size Factor Persistence: The size premium failed to reach new highs for nearly 30 years after 1981, yet remained widely accepted, illustrating how slow consensus shifts in factor investing.
Join our newsletter to have all of this content + Exclusive Newsletter Bonus Content delivered to your inbox every week
Related Content
