EP
Long high EP · rebalanced monthly · cap-weighted long-short
ib / lag(market value of equity, 6 months). NYSE stocks only. Exclude if EP < 0. Lag simulates the Dec 31 market equity used in original paper
Valuation: stocks that look cheap relative to fundamentals (earnings, book value, sales, cash flow) have historically out-earned expensive ones.
Growth of $1 — long-short
Energy only · cap-weighted · 331 months
The bottom-bucket figures are that basket’s ownreturn (a long position in what the strategy shorts) — not the short side’s P&L. Long-short return = long leg − bottom bucket, so a falling bottom bucket widens the spread.
’00–’12 · ’13–’18 · ’19–’26windows
Recomputes the split Sharpes and test alpha. Full Sharpe, ann. return, max drawdown and OAP correlation span the whole sample and don’t change.
Worked example
Live inputs for a real holding
| Input | Value |
|---|---|
| netinc | 122,575,000,000$ |
| Market cap | 4,901,758$M |
netinc / marketcap (drop if < 0)signed_value is the internal ranking value; only its cross-sectional rank matters. $-vs-$M unit mix means ratio magnitudes carry a constant offset and are not comparable to textbook levels.
Replication
How closely this rebuild tracks the published research
The OSAP comparison is only computed for the all-stocks variant — switch to “All stocks” above to see how the rebuild tracks the published series.
Style tilt
Size × value map of the long leg
Share of long-leg capital by market cap × book-to-market, using terciles of the 137-name universe at July 2026. Rows: Large ≥ $7.1B, Small < $1.8B. Columns: Value ≥ 0.64, Growth < 0.40 B/M. The dot marks the capital-weighted centroid of the book — 83% toward Large, 2% toward Growth. Hypothetical holdings — descriptive, not realized P&L.
Capital-weighted centroid of the long leg, December 1998 → July 2026; the right-hand end is the same value as the box’s dot. 20 names now. Hypothetical holdings — descriptive, not P&L.
Since publication
Did the edge survive the paper coming out?
There is no “before” to compare against — the predictor was already public when our data begins, so every month shown is out-of-sample relative to the original study.
Split at January of the year after the factor was published. The post-publication stretch IS genuinely out-of-sample relative to the original study -- the predictor was public by then -- so it speaks to whether the effect survived being known. Nothing is fitted here, so this is performance SINCE PUBLICATION, not validation of a model. Note the 'pre' side is our data before publication (our panel starts ~1999), NOT the study's original in-sample period, which usually ran decades earlier; a decay figure compares before-vs-after within our sample and is not a comparison against the published result.
Derivatives risk (Rule 18f-4)
Relative VaR against the designated reference portfolio — as implemented here
This assessment describes the research long-short construction — long the top bucket, short the bottom.
This fund does NOT qualify for the limited-derivatives-user exception (100% of net assets vs <= 10% of net assets), so the relative VaR test governs. Note the inversion: a dollar-neutral long-short book suppresses the market risk the VaR ratio measures and so tends to pass it, while being barred from the exception by construction — what disqualifies the strategy is the exposure threshold, not the risk limit.
Rule 18f-4(c)(4): a fund whose derivatives exposure (gross notional, including the value of assets sold short) is <= 10% of net assets is excepted from the VaR tests and the full derivatives risk management program.
No confidence interval: this follows from portfolio construction, not from an estimate.
Rule 18f-4(c)(2)(i): fund VaR at 99% over 20 trading days must not exceed 200% of the designated reference portfolio's VaR on the same basis.
Within the limit as implementedhistorical method · 331 monthly observations · about 3.3 in the 99% tail · paired percentile bootstrap over months
The estimators agree, which is mild evidence the number isn’t an artefact of one method.
Engineering approximation of SEC Rule 18f-4 for research display. Not a compliance opinion and not a determination that any fund is compliant. Hypothetical model portfolio, not a registered fund.
Consistency across eras
Is this record broadly durable, or one regime?
3-year rolling windows, stepping 1 year (26 windows). Dispersion is the spread of window Sharpes — higher means the record depends more on which era you look at.
Rules-based factors fit no parameters, so these windows are not out-of-sample tests and do not validate a fitted model. They show whether the factor's record is consistent across eras or driven by one regime.
Returns
Long-short is the research line; the long leg is what a long-only fund could hold
| Period | Long-short | Long leg |
|---|---|---|
| 1 yearcum. | 20.3% | 50.0% |
| 3 yearsp.a. | -12.6% | 7.9% |
| 5 yearsp.a. | -7.5% | 16.8% |
| 10 yearsp.a. | 3.6% | 13.2% |
| Since inceptionp.a. | 2.8% | 12.6% |
| Year | Long-short | Long leg |
|---|---|---|
| 20267 mo | 9.7% | 36.8% |
| 2025 | -3.2% | 1.3% |
| 2024 | -40.7% | -11.0% |
| 2023 | 24.0% | 15.3% |
| 2022 | 5.9% | 54.1% |
| 2021 | -25.8% | 22.1% |
| 2020 | 81.6% | 7.5% |
| 2019 | -5.7% | 9.3% |
| 2018 | 21.8% | -5.6% |
| 2017 | 1.5% | -4.1% |
| 2016 | -10.3% | 8.6% |
| 2015 | 53.2% | -7.4% |
| 2014 | -17.0% | -7.7% |
| 2013 | -11.2% | 23.4% |
| 2012 | -1.5% | 7.1% |
| 2011 | -0.4% | 13.8% |
| 2010 | -15.2% | 11.0% |
| 2009 | -7.1% | 35.9% |
| 2008 | -17.4% | -43.1% |
| 2007 | 4.5% | 34.2% |
| 2006 | 6.2% | 23.0% |
| 2005 | -14.5% | 34.2% |
| 2004 | 1.0% | 32.5% |
| 2003 | 12.8% | 30.9% |
| 2002 | 6.9% | -16.3% |
| 2001 | 63.8% | 11.3% |
| 2000 | 16.3% | 60.4% |
| 1999 | 15.0% | 34.2% |
Long-short is the research line (long the top bucket, short the bottom); the long leg alone is what a long-only fund could actually hold. Trailing figures run through July 2026: 1 year is a plain cumulative 12-month return (cum.), 3 years and longer are annualised (p.a.). Years marked with a month count are partial. These match the fact sheet’s tables by construction. Hypothetical backtest, gross of the placeholder expense ratio and trading costs — not investor results.
Methodology
Signal computed monthly from Sharadar point-in-time data, signed so higher = higher expected return. Restricted to the Energy sector, then sorted into quintiles within that sector. The virtual ETF is long the top bucket, short the bottom, cap-weighted, rebalanced monthly. FF5 alpha regresses the long-short on the Fama-French 5 factors.
Hypothetical research backtest. Not an offer, recommendation, or investment advice.