Size Factor - Small Capitalization Stocks Premium

The three-gate gauntlet · genuine only if it clears all three and survives adversarial refutation

Gate 1

Survivorship-free

free

clean panel

Gate 2

Placebo ≥ P95

P100

outranked ~200 of 200 baskets

Gate 3

Cost-aware net

RF +5.40

positive net, certified

Genuine

Worst 12-month leg (RF)-0.74

−1.00 floor0

Every strategy here — winners included — loses in its worst 12 months. Depth is honest context, not the verdict.

Cleared all three gates and adversarial refutation — a market-neutral diversifier with a losing worst year, not a standalone strategy.

The size effect is the long-documented tendency for smaller-capitalization stocks to earn higher average returns than the largest ones. This factor-leg goes long the smallest-decile names and short the largest-decile names, cross-sectionally.

What we found

The size premium survives our survivorship-free and placebo tests, indicating genuine rank-skill rather than an artifact of dead-company bias. It is a diversifying factor-leg, not a standalone tradeable strategy: its worst year is a loss (worst-year RF -0.74) and 6 of 22 years were negative. One load-bearing caveat matters most: our "small" leg is the smallest of roughly 1,045 liquid names (all above ~$50M/day of turnover), not the CRSP microcap tail where the classic textbook premium concentrates, so the tradeable version here is a muted subset of the paper.

How we tested it

2005–2026 test windowmodelled liquidity-aware costssurvivorship free

Tested on a survivorship-free 1077-name US common-stock panel, 2005-2026. Realistic modelled costs.
Placebo / robustness test: real result vs random baskets or shuffled signals (real vs the 95th percentile of random)

Source: Banz (1981), "The relationship between return and market value of common stocks", J. Financial Economics (SMB / Fama-French 1993)
Read the paper ↗

← The Academic Audit — all 54 studies

Research, not investment advice. “Validated” factor-legs are market-neutral diversifying building blocks with a losing worst year — none is a standalone tradeable strategy. Metrics are cost-aware and modelled (not live fills); the 2005–2026 test window is out-of-sample versus the source paper. Dollar figures are not returns and are omitted by design.