Anomaly Replication Lab
  • The zoo
  • Screener
  • Multiple testing
  • Correlations
  • Composite
  • Methodology
  • Guides
  • Resources
Sign in
Anomaly Replication LabSign in
  • The zoo
  • Screener
  • Multiple testing
  • Correlations
  • Composite
  • Methodology
  • Guides
  • Resources

Educational replication, not advice. Long-short returns are decile spreads or published factor series from the Kenneth R. French Data Library and AQR, value-weighted, US equities, and gross of transaction and shorting costs — which for high-turnover signals like short-term reversal is the whole story. Reproducing a premium in-sample is not evidence it will persist. Past performance does not predict future results.

© 2026 Austin Levenberg. All rights reserved. This site’s code, design, written analysis, and computed results are not licensed for reuse or redistribution — terms of use · privacy.

Data: Kenneth R. French Data Library, AQR Capital Management public data sets.

Part of austinlev.dev — four research tools, and a note on where this is headed.

← the zoo
QualityFaded

Net share issuance

Firms that issue stock underperform; firms that buy back outperform.

Pontiff & Woodgate; Daniel & Titman · Journal of Finance · published 2008 · original sample 1970–2003 (reported ≈ +8.0%/yr, t ≈ 3.5)

How our version differs from the paper. The original studies equal-weight and include microcaps; the value-weighted decile spread here is more conservative. The decay figure compares our replication in-sample to our replication after publication, so it isn’t affected by this — but the level gap between “reported” and “our replication” partly is.
Our replication
+3.8%
1963–2026, per year
Full-sample t
2.6
Sharpe 0.38
Post-publication
+3.4%
since 2009, t = 0.9
Decay
48%
of the premium is gone

The whole history

Growth of $1 in the long-short strategy, gross of trading and shorting costs. The dashed line marks the year the paper was published — everything to its right is out-of-sample.

$1 in the long-short strategy, gross of costs. Grey = the sample the paper had; blue = everything since.

Before and after publication

The comparison the site is built around.

WindowReturn/yrVolSharpet-statMax DD
Paper's sample (1970–2003)+6.0%11.3%0.582.9-34%
After publication (2009–2026)+2.4%14.3%0.240.9-38%
Full sample (1963–2026)+3.8%11.8%0.382.6-38%

Against the factor models

Is there a risk-adjusted alpha left once you control for the standard factors? Alpha is annualized; t-stats use Newey–West standard errors.

ModelAlpha/yrAlpha tR²Biggest loadings
CAPM (market only)+6.6%3.90.15Mkt-RF -0.29
Fama–French 3-factor+5.9%4.20.35SMB -0.49, HML +0.24, Mkt-RF -0.17
Fama–French 5-factor+3.1%2.30.47CMA +0.60, RMW +0.44, SMB -0.38
FF5 + momentum+2.8%2.20.47CMA +0.59, RMW +0.44, SMB -0.38

Rolling performance

Trailing 3-year Sharpe ratio. Long stretches below zero are common.

By decade

1960s-1.9%/yrSharpe -0.20
1970s+3.8%/yrSharpe 0.31
1980s+6.0%/yrSharpe 0.74
1990s+3.6%/yrSharpe 0.36
2000s+8.2%/yrSharpe 0.67
2010s+7.0%/yrSharpe 0.57
2020s+1.0%/yrSharpe 0.06

The risk explanation

Issuance changes leverage and therefore equity risk, but the effect is far too large to be a leverage story.

The behavioral explanation

Managers time the market — they issue when the stock is overvalued and repurchase when it is cheap — and investors don't fully adjust.

Why it might have decayed

Related to the older, weaker findings on IPO and SEO underperformance. Still one of the more robust quality signals, though buyback-heaviness since 2010 has muddied the short leg.

Long-short = top-decile minus bottom-decile of stocks univariately sorted on the characteristic. Value-weighted, US equities, monthly, gross of transaction and shorting costs. The original-paper figures are approximate and annualized for comparison.