Momentum Effect in Stocks in Small Portfolios

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 +2.31

positive, not certified

Failedfailed refutation

Worst 12-month leg (RF)-0.87

−1.00 floor0

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

Cleared the numeric checkpoints it reached but failed adversarial refutation — the positive figure is market beta or a single-period jackpot, not a repeatable edge.

The paper ranks stocks by their prior 12-month return and holds a small, concentrated portfolio of the strongest recent winners against the weakest recent losers. The idea under test is that momentum returns are larger when the winner and loser portfolios are held to a small number of names.

What we found

The rank signal is real: on a survivorship-free panel it lands at the top of the placebo distribution, so the ordering it produces is not noise. We still reject it as a standalone. Built the way the paper specifies — an extreme long-top-10 / short-bottom-10 concentration rather than the broad decile baskets used by our validated factor-legs — it is structurally tail-fragile: the worst-year RF is -0.87 (the 2016 momentum crash, a genuinely losing year), and the jackpot test is negative, meaning the multi-year result does not survive removing its top handful of contributor days. The earlier universe-contamination concern (a leveraged VIX ETN wrongly in the panel) was fixed and retracted; the clean signal still fails the genuine bar on tail grounds alone. It is not a tradeable system.

How we tested it

2005–2026 test windowmodelled liquidity-aware costssurvivorship free

Data: 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: Siganos (2007), "Momentum returns and size of winner and loser portfolios", Applied Financial Economics
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.