QuanterLab · Research

Paid to wait, paid less - dividend yield against earnings yield in total returns, twenty sealed windows of the S&P 500

A point-in-time walk-forward investigation with hypotheses registered before scoring and the size of the search left unreconstructed rather than guessed.

By Serhat Girgin

Universe · S&P 500 (point-in-time constituents)

Method · Comparative: Dividend yield vs Earnings yield

Manipulated variable · The value metric, and nothing else. Both arms load the same point-in-time S&P 500, compute value scores from the same SEC acceptedDate-gated filings, and rank on a single measure each: Arm A on trailing dividend yield - the income leg of value, the signal Litzenberger and Ramaswamy found priced in 1979 and Miller-Modigliani's 1961 irrelevance theorem says should not matter - and Arm B on earnings yield, asking whether the dividend is a signal of its own or earnings cheapness in disguise. Thirty best-ranked names each, equal weighted, long only, re-selected annually, twenty registered one-year wind

Step size · 1 year per forward window

In-sample · 2 years before each anchor

Out-of-sample span · 2006-01-03 → 2025-12-31

Compiled · August 15, 2026

Search record · none (size unknown, see §2.3)

Abstract

This is the first QuanterLab study to be measured the way a holder actually experiences an equity book: every dividend credited on its ex-date, every trade charged ten basis points, and the benchmark held to the same standard - an equal-weight S&P 500 with its own dividends reinvested. On that footing we asked the oldest question in income investing: does the dividend carry selection information of its own, or is it earnings cheapness in disguise? Two circuits rank the same point-in-time S&P 500, one on trailing dividend yield, one on earnings yield - thirty names, equal weight, re-selected annually, twenty sealed one-year windows, 2006 through 2025 - and differ in nothing else. The dividend book collected 4.6 percent a year in cash, more than double the index's 2.0, and compounded at 9.6 percent - almost exactly the total-return index's 9.5, on a worse Sharpe than the index. The earnings-yield book compounded at 11.0. And here is the conclusion the data actually supports: the 1.4-point annual gap between the two screens is not distinguishable from zero. The difference track's Sharpe is -0.12; a block bootstrap puts the dividend book ahead in 29 of 100 resampled twenty-year paths; each screen won about half the windows. What IS measurable is stranger: the two definitions of income value share a median of four names in thirty. Two portfolios with almost nothing in common, and no distinguishable difference in outcome - while the cash the dividend book collected was real, spendable, and fully given back by its price leg.

1 Methodology

Two sealed circuits, identical except the single active metric on the Value Factor node: Arm A ranks on trailing-twelve-month dividend yield, Arm B on earnings yield (both from SEC acceptance-dated filings; non-payers rank last at zero yield rather than dropping out, so both arms rank identical pools). Thirty highest-ranked names, equal weight, long only, annual re-selection, twenty one-year out-of-sample windows anchored each January from 2006.

The realism layer - identical in BOTH arms, so the single difference remains the ranking metric: returns are TOTAL returns, with each held name's dividend credited to the book on its ex-date (split-adjusted amounts matching the split-adjusted price series) and held as cash until the next rebalance; ten basis points of combined transaction cost charged on every one-way traded dollar (a full annual re-selection turns over roughly 1.0 times the book, so the charge lands near ten basis points of equity per year); and the RSP benchmark rebuilt as a total-return index by the same ex-date credit rule (its dividends added 2.03 points a year on average across these windows). Sharpe ratios are computed on raw daily returns without a cash hurdle. Every window's run report carries the full curve ladder - price-only, with dividends, net of costs - and machine gates verified per window that the total-return basis, the cost charge and the dividend accounting were live.

Lineage, in plain words: this circuit design has no recorded design history behind it, so the number of alternative specifications considered before it cannot be audited and no multiplicity correction is claimed. Two unregistered rehearsal runs of this exact circuit (at the 2006 and 2024 anchors) were executed immediately before registration as engine verification of the new total-return layer; no design change followed them, and they are disclosed here.

2 Results

2.1 Headline

Dividend yield, pooled Sharpe

0.51

5012 OOS bars

Earnings yield, pooled Sharpe

0.56

5012 OOS bars

P(Dividend yield beats Earnings yield)

29.1%

5011 paired bars · CAGR gap (Dividend yield − Earnings yield) -1.4 pp

Figure 1. Both arms stitched through the identical windows, Dividend yield (+496.2%), Earnings yield (+672.9%), benchmark grey (+515.1%, total return, its own dividends reinvested, pooled Sharpe 0.545). Dotted verticals mark the step boundaries; the dashed horizontal is break-even. These figures compound each arm's own stitched daily series; the pooled statistics in the text inner-join both arms' trading days, one session apart, both are printed from the frozen record.

Figure 2. The measurement ladder: Dividend yield's whole walk, chained five ways. price only (+153.3%), with dividends (+507.3%), net of costs (+496.2%), against the benchmark measured both ways: price only (+325.6%), total return (+515.1%). The distance between the two green pairs is the dividends collected; the sliver between the last two greens is the cost bill; the distance between the two greys is what a price-only chart hides about the index. Every other figure on this page uses the deepest rung on each side, net of costs against the total-return benchmark.

Figure 3. The same walk, re-based to 1.00x at the first window starting in 2011, 15 of the 20 windows above. Dividend yield (+473.1%), Earnings yield (+507.6%), benchmark grey (+427.8%, total return). This is a subset of Figure 1, not a correction to it. The era boundary here is pinned by the author at 2011, a break this study's own record shows, not a chart-scaling choice, and the era rows below put a number on the two periods it separates. The full record is what the study claims.

2.2 Per-step results

**Table 1.** One row per step, raw out-of-sample results.
#	Out-of-sample window	Dividend yield SR	Earnings yield SR
1	2006-01-03 → 2006-12-29	2.29	0.97
2	2007-01-03 → 2007-12-31	-0.03	0.77
3	2008-01-02 → 2008-12-31	-0.72	-0.84
4	2009-01-02 → 2009-12-31	0.68	1.00
5	2010-01-04 → 2010-12-31	0.77	0.82
6	2011-01-03 → 2011-12-30	0.54	-0.13
7	2012-01-03 → 2012-12-31	1.35	1.27
8	2013-01-02 → 2013-12-31	1.98	2.90
9	2014-01-02 → 2014-12-31	1.65	1.07
10	2015-01-02 → 2015-12-31	-0.37	-0.60
11	2016-01-04 → 2016-12-30	1.20	1.08
12	2017-01-03 → 2017-12-29	0.55	1.87
13	2018-01-02 → 2018-12-31	-0.09	-0.62
14	2019-01-02 → 2019-12-31	2.15	1.30
15	2020-01-02 → 2020-12-31	0.13	0.04
16	2021-01-04 → 2021-12-31	1.59	1.81
17	2022-01-03 → 2022-12-30	0.51	-0.49
18	2023-01-03 → 2023-12-29	0.64	1.14
19	2024-01-02 → 2024-12-31	1.33	1.36
20	2025-01-02 → 2025-12-31	0.47	1.28

Figure 4. Dividend yield: every step's out-of-sample curve overlaid, each rebased to 1× at its own start. Read alongside Table 1: consistent shape across steps is the walk-forward's evidence; a single lucky leg is not.

Figure 5. Earnings yield: the same windows, the other arm. Compare shape-for-shape with the previous figure: the two arms trade the identical out-of-sample legs.

2.3 Search accounting

No search record exists for this design. It was not promoted from a recorded evolving search, so the number of alternatives tried before it, on paper, in another tool, or in the author's head, is unknown. Unknown is a different fact from one: a study with no lineage is not a strategy with one trial, it is a strategy with an unrecorded number of them. Accordingly no count of alternatives tried is claimed, and nothing in this paper is corrected for a search that was never recorded; the number that stands is the raw out-of-sample result plus this disclosure. The registered per-step record below (§4) still guarantees each window's hypothesis was hashed and registered before that window was scored.

2.4 The comparison

Both arms trade the same registered windows, so their returns can be PAIRED: inside each window the two return series are inner-joined date by date and the difference r_{Dividend yield} − r_{Earnings yield} is the object under test. Because this is ONE pre-declared contrast, frozen at registration before any window was scored, the paired statistic needs no multiple-testing deflation, and the per-arm pooled numbers above are likewise uncorrected, this design has no recorded search to correct against (§2.3). The paired contrast is the one statistic here that a missing search record does not weaken: it was declared in advance, and it is scored on the difference rather than on either arm's level.

**Table 2.** Window-by-window paired comparison. Δ is the growth gap (Dividend yield − Earnings yield) over the window's paired dates.
#	Window	Paired bars	Dividend yield	Earnings yield	Δ	Leader
1	2006-01-04 → 2006-12-29	250	+22.5%	+11.5%	+11.0 pp	Dividend yield
2	2007-01-04 → 2007-12-31	250	-2.0%	+13.9%	-15.8 pp	Earnings yield
3	2008-01-03 → 2008-12-31	252	-37.2%	-34.6%	-2.6 pp	Earnings yield
4	2009-01-05 → 2009-12-31	251	+23.1%	+32.4%	-9.3 pp	Earnings yield
5	2010-01-05 → 2010-12-31	251	+12.6%	+16.2%	-3.7 pp	Earnings yield
6	2011-01-04 → 2011-12-30	251	+9.0%	-7.0%	+16.0 pp	Dividend yield
7	2012-01-04 → 2012-12-31	249	+16.5%	+22.5%	-5.9 pp	Earnings yield
8	2013-01-03 → 2013-12-31	251	+24.2%	+50.8%	-26.7 pp	Earnings yield
9	2014-01-03 → 2014-12-31	251	+16.7%	+14.2%	+2.5 pp	Dividend yield
10	2015-01-05 → 2015-12-31	251	-6.2%	-11.4%	+5.3 pp	Dividend yield
11	2016-01-05 → 2016-12-30	251	+27.7%	+21.8%	+5.9 pp	Dividend yield
12	2017-01-04 → 2017-12-29	250	+4.3%	+22.0%	-17.7 pp	Earnings yield
13	2018-01-03 → 2018-12-31	250	-2.2%	-9.8%	+7.6 pp	Dividend yield
14	2019-01-03 → 2019-12-31	251	+27.5%	+21.7%	+5.8 pp	Dividend yield
15	2020-01-03 → 2020-12-31	252	-4.7%	-8.1%	+3.4 pp	Dividend yield
16	2021-01-05 → 2021-12-31	251	+38.1%	+42.0%	-3.9 pp	Earnings yield
17	2022-01-04 → 2022-12-30	250	+9.3%	-13.8%	+23.1 pp	Dividend yield
18	2023-01-04 → 2023-12-29	249	+9.5%	+20.4%	-11.0 pp	Earnings yield
19	2024-01-03 → 2024-12-31	251	+20.6%	+23.8%	-3.1 pp	Earnings yield
20	2025-01-03 → 2025-12-31	249	+7.0%	+30.0%	-23.0 pp	Earnings yield

Paired Sharpe of the difference track: -0.12 · block bootstrap (2000 paths, block 10, seed 1234): P(Dividend yield beats Earnings yield) = 29.1%.

Window win-rate. Dividend yield led 9 of 20 windows (45.0%), Earnings yield led 11 , and the mean window gap of -2.11 pp points the same way. Widest single window: 2013 at -26.7 pp.

**Table 3.** The same comparison split at 2011. Pooling the whole walk into one row hides which side of the split the difference came from.
Period	Windows	Dividend yield	Earnings yield	Mean gap	Dividend yield led
All windows	20	+10.82%	+12.93%	-2.11 pp	9/20
Before 2011	5	+3.80%	+7.88%	-4.08 pp	1/5
2011 onward	15	+13.15%	+14.61%	-1.45 pp	8/15

Figure A1, mean window return per period. Dividend yield above, Earnings yield below, with the gap at right. The pooled bar and the post-2011 bar are the same comparison over different periods.

The two eras disagree by 2.63 pp. The pooled figure is therefore not a standing property of either method, it is dominated by the earlier period. Read the two rows, not the average.

3 The circuit

The strategy is a circuit of platform primitives, frozen when the study is registered. Below is the circuit as wired on the canvas, the objective it encodes and how the search runs through it, followed by the mathematics each primitive actually computes, the same formulas the execution engine runs. The complete parameterisation is preserved in the study ledger (Appendix A).

The hypothesis under test

A COMPARATIVE study, Dividend yield vs Earnings yield, walked on the same registered out-of-sample windows. Dividend yield: S&P 500, rebalanced annual across the selected basket, and run out-of-sample from the anchor, whatever the design estimates from history is re-estimated at each anchor from pre-anchor data only, and the walk advances through registered out-of-sample windows; its disposition is the realized forward path versus the benchmark. Earnings yield: S&P 500, rebalanced annual across the selected basket, and run out-of-sample from the anchor, whatever the design estimates from history is re-estimated at each anchor from pre-anchor data only, and the walk advances through registered out-of-sample windows; its disposition is the realized forward path versus the benchmark. The arms differ in: Value Factor, dividend_yield: high → off; Value Factor, earnings_yield: off → high. The contrast under test: whether Dividend yield generates better risk-adjusted returns than Earnings yield over the identical out-of-sample windows.

Figure 6. The frozen circuit, every node a primitive, every wire a typed data-flow; the two arms are colour-coded (Dividend yield green, Earnings yield blue, shared feeds neutral). Each box is one step of the strategy; data flows along the wires left to right, and no box can see data dated later than the box feeding it. The whole diagram was frozen when the hypothesis was registered. Click any node to open what that step ran with and what it produced.

Envelopes show counts, ratios, dates, and the parameters the author chose. Full price and per-name data series are not republished: the underlying market data is licensed to QuanterLab. Point figures quoted in the prose, a named holding's return over a stated span, are summary facts derived from public market prices, not redistributed series.

What each part does

Universe, The starting set of tickers, resolved point-in-time from the index change-log, so names delisted or removed later still compete on the dates they traded.

Price Loader, Bulk OHLCV fetch for the whole universe, point-in-time, no future bars.

Factor Loader, Point-in-time fundamentals, never let the user see a number before the SEC did.

Factor Value, Value, how cheap is the stock, cross-sectionally?

Factor Composite, The weighting console, blend Value, Quality, Momentum, Growth into one 0–100 score.

Factor Top Tier, The cut out of the factor lane, keep the top-ranked names.

Portfolio Backtest, Replay the portfolio forward, rebalanced, point-in-time, with costs.

Transaction Cost, Charge for trading, slippage + commission on every turn.

Portfolio Forward Autopsy, The post-mortem, where the forward test’s return actually came from.

The objective and the search

Dividend yield

Universe	S&P 500 index constituents.
Validation & out-of-sample	portfolio forward test (buy-and-hold book) (1y horizon from the anchor, annual rebalance); overlays: Transaction Cost.
Other components	Factor models: Factor Composite, Factor Select, Fundamentals Loader (PIT), Value Factor.

Earnings yield

Universe	S&P 500 index constituents.
Validation & out-of-sample	portfolio forward test (buy-and-hold book) (1y horizon from the anchor, annual rebalance); overlays: Transaction Cost.
Other components	Factor models: Factor Composite, Factor Select, Fundamentals Loader (PIT), Value Factor.

What differs between the arms, one manipulated variable, expressed as 2 paired settings on one node:

paramValue Factor, dividend_yield: high → off
paramValue Factor, earnings_yield: off → high

Everything else is held identical, so an out-of-sample gap between the arms is attributable to this one change.

Cost elements are wired into the circuit, the realised drag is reported per step in Appendix B.

Show the mathematics, 9 primitives, formulas and parity notes

3.1 Universe

The starting set of tickers, resolved point-in-time from the index change-log, so names delisted or removed later still compete on the dates they traded.

Before any math, you need a list of stocks. An index preset (S&P 500, Nasdaq-100, Dow 30) is reconstructed as it stood ON your anchor date by replaying the historical add/drop change-log backwards, so a 2018 backtest sees the 2018 membership, not today's winners.

Point-in-time membership

Start from today's constituents and un-apply every membership change after the anchor t:

\mathcal{U}(t) = \mathcal{U}_{\text{now}} \;\ominus\; \{\text{adds after } t\} \;\oplus\; \{\text{drops after } t\}

Constituents resolved from the index change-log; the same point-in-time set the factor + screening modules use.

3.2 Price Loader

Bulk OHLCV fetch for the whole universe, point-in-time, no future bars.

Momentum, volatility, trend, every price-based metric needs history. This loads open/high/low/close/volume for all names in parallel, clipped so nothing after the anchor can leak in. The lookback window is derived automatically from the deepest metric you wired.

The window is derived, not guessed

It loads exactly enough history for the hungriest downstream metric plus a warm-up buffer:

W = \max_k(\text{lookback}_k) + \text{buffer}, \qquad \text{bars} \le \text{anchor } t

3.3 Factor Loader

Point-in-time fundamentals, never let the user see a number before the SEC did.

Loads ~23 fundamental metrics (valuation, quality, growth) per name, but with one inviolable rule: a financial statement becomes visible only on or after its SEC acceptedDate. A 2020 backtest sees only what was actually filed by 2020, no look-ahead, ever.

The PIT gate

\text{visible}(f, t) \iff \text{acceptedDate}(f) \le t

Missing acceptance dates fall back to filingDate, else statement date + 45 days.

Byte-identical to FM101FBKT (shared_libs/factor_core). US indexes only (SEC reliability).

3.4 Factor Value

Value, how cheap is the stock, cross-sectionally?

Blends cheapness metrics, P/E, P/B, P/S, EV/EBITDA (lower is better) plus free-cash-flow and earnings yields (higher is better). Each metric is z-scored across the universe, winsorized against outliers, weighted by the importance you set (Off/Low/Med/High), and averaged.

Cross-sectional z-score per metric

z_{i,k} = \pm\,\frac{x_{i,k} - \bar x_k}{s_k}

Sign encodes direction (cheap = good). Winsorized at 1% / 99%.

Importance-weighted family score

\text{Value}_i = \frac{\sum_k \omega_k\,z_{i,k}}{\sum_k \omega_k}, \quad \omega \in \{0,\,0.5,\,1,\,2\}

Off / Low / Medium / High = 0 / 0.5 / 1 / 2. Binding rank happens in Factor Composite.

Byte-identical to FM101FBKT (shared_libs/factor_core).

3.5 Factor Composite

The weighting console, blend Value, Quality, Momentum, Growth into one 0–100 score.

Where the four factor families become a single ranking. Each family score is standardized across the universe, blended with your slider weights (or the radar's suggested tilt), and min-max scaled to 0–100. Winsorizing tames outliers; z-score or percentile normalization is your choice.

Cross-sectional standardize + winsorize

z_{i,f} = \frac{x_{i,f} - \bar x_f}{s_f}\quad(\text{clipped at the 1st / 99th percentile})

Weighted blend, scaled to 0–100

C_i = \sum_f W_f\,z_{i,f}, \qquad \text{score}_i = 100\cdot\frac{C_i - \min_j C_j}{\max_j C_j - \min_j C_j}

W = your four slider weights (total 100) OR the Regime Tilt radar's suggestion. Needs ≥ 10 names, ≥ 3 valid metrics each.

Byte-identical to FM101FBKT ranking (shared_libs/factor_core.rank_stocks_at_date).

3.6 Factor Top Tier

The cut out of the factor lane, keep the top-ranked names.

Takes the composite-ranked factor set and keeps the best N, carrying the composite score, the four family scores and the point-in-time market cap for each survivor. Feed 10–20 to a direct portfolio, or 30–100 as an optimizer pool.

Rank cut

\{\, i : \operatorname{rank}(C_i) \le N\,\}, \quad C_i = \text{composite score}

Byte-identical to FM101FBKT ranking (shared_libs/factor_core).

3.7 Portfolio Backtest

Replay the portfolio forward, rebalanced, point-in-time, with costs.

Holds the basket and rebalances on schedule, re-selecting and re-optimizing point-in-time at each rebalance (so it only ever uses information available then), and reports the equity curve, Sharpe, drawdown and trade stats, optionally net of cost and risk overlays.

Compounded equity

E_t = E_{t-1}\big(1 + \mathbf w_{t}^{\top}\mathbf r_t - \text{costs}_t\big)

Drawdown

\text{DD}_t = \frac{E_t}{\max_{\tau\le t}E_\tau} - 1, \qquad \text{MaxDD} = \min_t \text{DD}_t

Financing a levered book

\text{charge}_t \;=\; \text{loan}_t \cdot \frac{\text{spread}}{252}, \qquad \text{loan}_t = \begin{cases}\max(0,\,-\text{cash}_t) & \text{institutional (netted)}\\ \max(0,\,\text{long MV}_t - E_t) & \text{retail (no netting)}\end{cases}

A levered long/short book (the β-neutral Long/Short Select) borrows its excess notional. WHO you are decides the loan: a prime broker nets short-sale proceeds against the margin loan, a fully-netted BAB book carries almost none, while a retail margin account cannot net, so the same book borrows the long leg’s excess over equity. Profiles: institutional = 50 bps spread + 25 bps GC short borrow; retail = 350 bps + 150 bps (the BEST retail tier, so any verdict is conservative); custom = your own knobs, spread on negative cash. Charged daily, reported as financing_drag_pct, never silent.

3.8 Portfolio Forward Autopsy

The post-mortem, where the forward test’s return actually came from.

Runs after the Portfolio Forward Test and dissects its realized path: per-rebalance contributions, winners and losers, exposure and cash periods, and how the realized route compares to what the risk cones projected. It computes nothing new about the future, it explains the past the book just lived.

Reading it

Depth I–IV: headline attribution, per-segment breakdown, per-name contributions, and the calibration ledger (projected cone vs realized, segment by segment). In a study, this is the node that fills the appendices.

3.9 Transaction Cost

Charge for trading, slippage + commission on every turn.

Real trading isn't free. This deducts a cost proportional to how much you trade (turnover), in basis points, so the backtest reflects net, not gross, performance.

Cost per rebalance

\text{cost}_t = \frac{\text{bps}}{10{,}000}\;\times\;\text{turnover}_t, \qquad \text{turnover}_t = \tfrac12\sum_i \lvert w_{i,t}-w_{i,t^-}\rvert

4 Projection calibration, pooled across the walk

Every rebalance carried a Monte Carlo cone and a 95% VaR estimated before the segment it is scored against. Two questions, pooled over the whole study: did realized outcomes land inside the band as often as the band claims, and were VaR breaches as frequent as 5%?

This section is produced by the forward tester itself: every portfolio backtest fits the cone and the VaR estimate at each rebalance and scores them against the segment that followed. It does not require, and this circuit does not contain, a Monte Carlo primitive; that primitive is a separate, standalone analysis.

Figure A2, projected range versus what occurred, at each of 40 scored rebalance segments, pooled across both arms. The final rebalance of each step has no following segment to score, the ledger marks those rows “no segment follows this rebalance”, which is why this count sits below the raw rebalance totals in the table beneath. Each vertical bar is that rebalance's P5–P95 Monte Carlo cone with the median ticked; the dot is the realized return of the segment that followed. Filled green = the outcome landed inside its own cone; red = it did not. The strip beneath repeats that as one mark per rebalance, so a run of misses in one period is visible as a run. Every cone was fitted only on data prior to the segment it is scored against.

Arm	Steps	Rebalances	In band	Coverage	Expected	VaR days	Breach rate	Expected
Dividend yield	20	35	14 / 20	70.0% ±10.25	90.0%	4938	6.72% ±0.356	5.0%
Earnings yield	20	35	18 / 20	90.0% ±6.71	90.0%	5011	5.81% ±0.33	5.0%

± values are binomial standard errors on the estimate. A coverage figure below the expected band means the projection was over-confident; a breach rate above 5% means the same of the risk model. Both forecasts used only data prior to the segment scored.

5 Discussion

5.1 Findings

Pooled over 5,011 paired out-of-sample days, the earnings-yield book earned a Sharpe of 0.565 against 0.505 for the dividend book, compounding at 11.0 against 9.6 percent a year. The honest index sits between them: the equal-weight benchmark with dividends reinvested compounded at 9.5 percent with a Sharpe of 0.545 - so the dividend book matched the index's compound return on a worse risk-adjusted footing (annualised volatility 23.5 percent against the index's 20.7), and the earnings book beat it by a point and a half a year. Sharpe ratios here are raw daily-return Sharpes, no cash hurdle.

Three statistics agree on how far apart the two screens are, and the answer is: not measurably. The paired difference track has a Sharpe of -0.12 - about half a standard error over twenty years. A block bootstrap of the daily differences (2,000 resampled paths, ten-day blocks) finishes with the dividend book ahead in 29.1 percent of paths. The dividend book won nine windows of twenty. The 1.4-point gap leans toward earnings yield; twenty years of sealed evidence cannot certify the lean, and the record itself says why: these two nearly-disjoint books diverge by about twelve points in a typical year - single years hit twenty-three and twenty-seven - so one 2022 outweighs sixteen years of the average lean, and at this lean-to-noise ratio roughly two hundred and eighty years of history would be needed to certify the direction. The null is the verdict on WHICH screen is better; the structure of the two books, the cash they collected and the risk they ran are measured facts, not estimates.

The money in motion deserves its own ledger. The dividend book collected 4.63 percent a year in cash on average - its heaviest window paid 6.7 - against 2.80 percent for the earnings book and 2.03 points for the index itself. Nearly half of the dividend book's compound return arrived as cash, and its price leg gave back what the income leg collected. Costs, at this cadence, are almost a footnote: one annual re-selection turns over about one time the book's value in one-way traded dollars, and ten basis points on that flow cost each arm one dime per hundred dollars per year, every window, identically. The realism layer did not decide this study; it priced it.

The averages hide texture that a holder would have lived through. In three correction years the dividend book was a genuine shelter - 2011 (up 9.0 against the index's -0.8 and the earnings book's -7.0), 2018 (down 2.2 against -8.5 and -9.8), and the 2022 rate shock (up 9.3 against -11.7 and -13.8). In two other down-tilted windows, 2015 and 2020, it beat the earnings book but not the index - and the 2020 window ended with the index up 12.4, so nothing needed sheltering. The record also keeps the dividend book honest about the crisis that mattered most: going into 2007-2008 its yield was substantially financial-sector yield about to be cut; it trailed the earnings book by 15.8 points in 2007, fell 37.2 percent in 2008 against the earnings book's 34.6, and its worst drawdown over the full record (50.4 percent) is deeper than the earnings book's 49.0. The shelter is three specific years, not a volatility property - the two books' volatilities are nearly identical.

The earnings book collected its advantage in the melt-ups: 50.8 percent in the 2013 window (26.7 ahead), 17.7 ahead in 2017, 23.0 ahead in 2025.

Structurally, the two books share a median of four names of the thirty selected - once, in the 2019 and 2020 windows, a single name - on ranked pools that are identical for both arms in every window (348 names in 2006, 504 by 2024). Two definitions of income value; almost no common holdings.

5.2 Interpretation

Why did anyone expect indifference? Miller and Modigliani argued in 1961 that, absent frictions, a firm's payout policy should not change its value - the canonical reason economists treat the dividend as financial plumbing rather than signal. Strictly, the theorem makes no prediction about ranking stocks on yield: dividend yield has price in its denominator, so sorting on it is partly sorting on cheapness, which the theorem never addresses. The operational null this study tests is narrower and fairer: does the dividend add selection information beyond the cheapness it proxies? Twenty sealed years answer: none that this record can certify - and the direction of the uncertified lean favours plain earnings cheapness. Meanwhile the income itself behaved exactly as the plumbing view predicts: the 4.6 percent a year the dividend book collected in cash was real and spendable, and its price leg gave it back - the market handed the income out of one pocket and took it from the other.

What the plumbing view does not describe is who the payers ARE. Fama and French documented in 2001 that the population of payers was shrinking and changing character, and this book wears that history. Its post-2010 vintages are anchored by the record's own names - Altria, Verizon, Walgreens, 3M, the regional banks and REITs of the yield aisle - and in three rate-and-risk corrections (2011, 2018, 2022) that composition was a real cushion. Its 2007 vintage was anchored by the financial sector's about-to-be-cut payouts, and the cushion failed exactly when it was needed most. Yield is a promise written by the past; earnings are the capacity to keep it.

The practical sentence for the income aisle: over twenty honest years, on the five hundred most-watched stocks in the world, a high-dividend book bought the index's compound outcome with thirty stocks' concentration and a lower Sharpe than the index it matched; the boring cheapness screen it allegedly proxies pointed 1.4 points a year better, and even that lead is within the noise. If you hold the dividend book, hold it for the three corrections and the cash in hand - not for the total return, which this record says you could have had by owning the index.

No search record exists for this study: the design was not promoted from a recorded evolving search, so the number of alternatives tried before it is UNKNOWN, which is a different fact from one. No count of alternatives tried is claimed, and nothing is corrected for a search that was never recorded; the number that stands is the raw out-of-sample result plus this disclosure. The out-of-sample windows are historical.

5.3 Limitations

The statistical conclusion is a null: the 1.4-point annual gap between the screens is not distinguishable from zero on this record, and every directional phrase in this paper should be read under that ceiling. Dividends are credited gross: no withholding, no dividend taxation, no reinvestment between rebalances. Costs are a flat ten basis points per one-way traded dollar; no market-impact scaling, no commissions, and capital-gains tax is not modelled. The yield variable is the trailing-twelve-month yield from filings - closer to Black and Scholes' (1974) long-run yield construction than to Litzenberger and Ramaswamy's ex-dividend-month measure, so this is not a test of their exact variable. The ranked pool is thinner early: 348 of roughly 500 index members carried usable fundamentals in 2006, rising to 504 listings (the index counts more than 500 share classes) by 2024 - the pre-2011 windows rest on materially thinner coverage, in both arms identically. The correction-year pattern and the 2007-08 financial-sector reading are descriptions of this record stated after seeing it, not pre-registered claims; the named holdings above are from the record's own appendix. Each arm is one metric, not a composite; nothing here speaks to dividend-growth screens, blended income strategies, or small caps. The engine held twenty-eight to thirty of the thirty selected names per window; a name with no usable entry bar is skipped at buy and weights renormalize, with counts disclosed per window.

References

QuanterLab reference architecture

Gelman, A., & Loken, E. (2013). The garden of forking paths: Why multiple comparisons can be a problem, even when there is no “fishing expedition.” Working paper, Columbia University.
Harvey, C. R., Liu, Y., & Zhu, H. (2016). … and the Cross-Section of Expected Returns. Review of Financial Studies, 29(1), 5–68. doi:10.1093/rfs/hhv059
Lo, A. W. (2002). The Statistics of Sharpe Ratios. Financial Analysts Journal, 58(4), 36–52. doi:10.2469/faj.v58.n4.2453

Author’s references?

Miller, M. H. and Modigliani, F. (1961). Dividend Policy, Growth, and the Valuation of Shares. Journal of Business 34(4).
Black, F. and Scholes, M. (1974). The Effects of Dividend Yield and Dividend Policy on Common Stock Prices and Returns. Journal of Financial Economics 1(1).
Litzenberger, R. H. and Ramaswamy, K. (1979). The Effect of Personal Taxes and Dividends on Capital Asset Prices: Theory and Empirical Evidence. Journal of Financial Economics 7(2).
Fama, E. F. and French, K. R. (2001). Disappearing Dividends: Changing Firm Characteristics or Lower Propensity to Pay? Journal of Financial Economics 60(1).

Appendix A Reproducibility in QuanterLab

Each step is backed by a frozen run report. The study is re-derivable from the ledger below.

#	Commit	Report	Anchor	OOS window
1	320a9a09b568	1201	2006-01-01	2006-01-03 → 2006-12-29
2	db8aef1fb81a	1202	2007-01-01	2007-01-03 → 2007-12-31
3	2fef64a5e4ef	1203	2008-01-01	2008-01-02 → 2008-12-31
4	50feb689e0be	1204	2009-01-01	2009-01-02 → 2009-12-31
5	687b94f5ff34	1205	2010-01-01	2010-01-04 → 2010-12-31
6	29c7f0c9d3a1	1206	2011-01-01	2011-01-03 → 2011-12-30
7	36d812597ed3	1207	2012-01-01	2012-01-03 → 2012-12-31
8	462b2f321135	1208	2013-01-01	2013-01-02 → 2013-12-31
9	1ba0746c2b23	1209	2014-01-01	2014-01-02 → 2014-12-31
10	177809db4855	1210	2015-01-01	2015-01-02 → 2015-12-31
11	3eb63f2c0bcf	1211	2016-01-01	2016-01-04 → 2016-12-30
12	321df532c4d8	1212	2017-01-01	2017-01-03 → 2017-12-29
13	39146d3b5b5c	1213	2018-01-01	2018-01-02 → 2018-12-31
14	f9129f835c45	1214	2019-01-01	2019-01-02 → 2019-12-31
15	86b01b728757	1215	2020-01-01	2020-01-02 → 2020-12-31
16	2d65285c16ba	1216	2021-01-01	2021-01-04 → 2021-12-31
17	a7cfbb788d96	1217	2022-01-01	2022-01-03 → 2022-12-30
18	7b68e67f40c0	1218	2023-01-01	2023-01-03 → 2023-12-29
19	21307b512021	1219	2024-01-01	2024-01-02 → 2024-12-31
20	257282cfb544	1220	2025-01-01	2025-01-02 → 2025-12-31

Appendix A2 Registration record

What this record does and does not establish. Every window in this study is historical: the data existed before the study began, so this is sequential sealing on past windows, not pre-registration in the clinical-trial sense, and no procedure could make it so. What the platform does enforce is order, each step's specification was frozen and hashed before that step was scored, and the walk cannot advance past a step that was never run or close one with a result registered for a different window. The two timestamp columns below are the evidence: read them together and each seal precedes its own run, and each run precedes the next seal. A study whose seals all post-date its runs would show it here. Wall-clock spacing between seals varies with the author's schedule and queue latency; the ordering, not the tempo, is the claim.

“A COMPARATIVE study, Dividend yield vs Earnings yield, walked on the same registered out-of-sample windows. Dividend yield: S&P 500, rebalanced annual across the selected basket, and run out-of-sample from the anchor, whatever the design estimates from history is re-estimated at each anchor from pre-anchor data only, and the walk advances through registered out-of-sample windows; its disposition is the realized forward path versus the benchmark. Earnings yield: S&P 500, rebalanced annual across the selected basket, and run out-of-sample from the anchor, whatever the design estimates from history is re-estimated at each anchor from pre-anchor data only, and the walk advances through registered out-of-sample windows; its disposition is the realized forward path versus the benchmark. The arms differ in: Value Factor, dividend_yield: high → off; Value Factor, earnings_yield: off → high. The contrast under test: whether Dividend yield generates better risk-adjusted returns than Earnings yield over the identical out-of-sample windows.”

The same hypothesis was registered independently at every step, hashed before each step's out-of-sample window was scored:

**Table 4.** Registration audit, one row per registered step, with the time each specification was frozen and the time its window was scored. The hypothesis is identical on every row by design: it was registered once and re-registered unchanged at each anchor. Rows that differ would mean the specification moved mid-walk, which is the thing this record exists to rule out. The timestamps are the separate claim: each seal precedes its own run, and each run precedes the next seal.
#	Anchor	Registered at (UTC)	Run completed (UTC)
1	2006-01-01	2026-08-15 15:34:30	2026-08-15 15:37:19
2	2007-01-01	2026-08-15 15:37:24	2026-08-15 15:40:44
3	2008-01-01	2026-08-15 15:40:49	2026-08-15 15:43:10
4	2009-01-01	2026-08-15 15:43:15	2026-08-15 15:47:15
5	2010-01-01	2026-08-15 15:47:21	2026-08-15 15:51:01
6	2011-01-01	2026-08-15 15:51:06	2026-08-15 15:54:47
7	2012-01-01	2026-08-15 15:54:52	2026-08-15 15:57:12
8	2013-01-01	2026-08-15 15:57:18	2026-08-15 16:01:19
9	2014-01-01	2026-08-15 16:01:24	2026-08-15 16:05:24
10	2015-01-01	2026-08-15 16:05:29	2026-08-15 16:09:30
11	2016-01-01	2026-08-15 16:09:35	2026-08-15 16:12:15
12	2017-01-01	2026-08-15 16:12:21	2026-08-15 16:16:41
13	2018-01-01	2026-08-15 16:16:46	2026-08-15 16:20:47
14	2019-01-01	2026-08-15 16:20:52	2026-08-15 16:25:13
15	2020-01-01	2026-08-15 16:25:18	2026-08-15 16:27:58
16	2021-01-01	2026-08-15 16:28:03	2026-08-15 16:32:24
17	2022-01-01	2026-08-15 16:32:29	2026-08-15 16:36:30
18	2023-01-01	2026-08-15 16:36:35	2026-08-15 16:40:35
19	2024-01-01	2026-08-15 16:40:40	2026-08-15 16:43:21
20	2025-01-01	2026-08-15 16:43:26	2026-08-15 16:47:46

Appendix B Per-step diagnostics

What each step's run actually did beyond its return: capital allocation across lanes and regimes, the portfolio book's rebalancing and cost drag, and how positions were sized. Harvested from the frozen run reports, present where the circuit produced them.

Step 1 · 2006-01-03 → 2006-12-29

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 29 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 1 name dropped at load (29 names actually held across the window), weights renormalised onto the rest

Projection accuracy, realized outcome fell inside the P5–P95 cone in 100.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 4.4% of 250 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2006-01-01	-8.3836%	7.6282%	26.8032%	18.8981%	yes	1.017%	11 / 250
2007-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 28 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 2 names dropped at load (29 names actually held across the window), weights renormalised onto the rest

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2006-01-01	-8.8454%	14.5185%	44.459%	8.7529%	yes	1.4596%	10 / 250
2007-01-01	no segment follows this rebalance, not scored

Step 2 · 2007-01-03 → 2007-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 15.6% of 250 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2007-01-01	-3.3953%	14.5014%	36.1267%	-7.9045%	no	1.093%	39 / 250
2008-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 1 name dropped at load (29 names actually held across the window), weights renormalised onto the rest

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2007-01-01	-2.3104%	22.4512%	54.1106%	4.089%	yes	1.4942%	25 / 250
2008-01-01	no segment follows this rebalance, not scored

Step 3 · 2008-01-02 → 2008-12-31

Dividend yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 27.78% of 252 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2008-01-01	-22.0627%	0.2078%	27.101%	-37.6556%	no	1.516%	70 / 252

Earnings yield

Portfolio book, rebalanced annual · 1 constructions · 29 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 1 name dropped at load (29 names actually held across the window), weights renormalised onto the rest

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 26.59% of 252 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2008-01-01	-10.8888%	13.7295%	43.245%	-39.5316%	no	1.4405%	67 / 252

Step 4 · 2009-01-02 → 2009-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 28 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 2 names dropped at load (30 names actually held across the window), weights renormalised onto the rest

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 9.96% of 251 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2009-01-01	-65.3809%	-31.4074%	37.3247%	41.7681%	no	3.6661%	25 / 251
2010-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2009-01-01	-51.8194%	-13.36%	57.194%	33.3459%	yes	3.1893%	18 / 251
2010-01-01	no segment follows this rebalance, not scored

Step 5 · 2010-01-04 → 2010-12-31

Dividend yield

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2010-01-01	-48.1207%	-5.5993%	73.3424%	8.8037%	yes	3.5472%	1 / 251
2011-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2010-01-01	-51.8662%	-2.8784%	98.0672%	15.3183%	yes	4.2986%	0 / 251
2011-01-01	no segment follows this rebalance, not scored

Step 6 · 2011-01-03 → 2011-12-30

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2011-01-01	-30.1116%	8.8626%	70.7168%	5.1583%	yes	2.7505%	7 / 251
2012-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2011-01-01	-32.6382%	21.8297%	122.3317%	-9.2223%	yes	3.6088%	7 / 251
2012-01-01	no segment follows this rebalance, not scored

Step 7 · 2012-01-03 → 2012-12-31

Dividend yield

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2012-01-01	-22.4059%	8.2252%	48.6264%	9.1734%	yes	2.1947%	1 / 249

Earnings yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2012-01-01	-33.6603%	3.1212%	57.035%	18.307%	yes	2.8267%	2 / 249

Step 8 · 2013-01-02 → 2013-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2013-01-01	-21.654%	4.6486%	40.3977%	18.9707%	yes	1.7657%	3 / 251
2014-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2013-01-01	-28.4054%	4.5478%	53.549%	50.415%	yes	2.2436%	4 / 251
2014-01-01	no segment follows this rebalance, not scored

Step 9 · 2014-01-02 → 2014-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2014-01-01	-12.0925%	8.2693%	33.77%	10.3388%	yes	1.3074%	8 / 251
2015-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2014-01-01	-4.6169%	25.6151%	66.1226%	8.7087%	yes	1.6803%	10 / 251
2015-01-01	no segment follows this rebalance, not scored

Step 10 · 2015-01-02 → 2015-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 10.76% of 251 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2015-01-01	-9.1025%	8.5131%	29.8916%	-11.9924%	no	1.1229%	27 / 251
2016-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 29 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 1 name dropped at load (30 names actually held across the window), weights renormalised onto the rest

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 8.37% of 251 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2015-01-01	-2.5236%	22.9939%	55.7405%	-15.9974%	no	1.4804%	21 / 251
2016-01-01	no segment follows this rebalance, not scored

Step 11 · 2016-01-04 → 2016-12-30

Dividend yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2016-01-01	-32.4989%	-12.155%	14.7788%	27.9221%	no	1.7009%	23 / 251

Earnings yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2016-01-01	-21.5092%	4.4309%	39.5478%	19.3938%	yes	1.7767%	17 / 251

Step 12 · 2017-01-03 → 2017-12-29

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2017-01-01	-23.7716%	-2.0522%	26.4212%	0.5684%	yes	1.6196%	2 / 250
2018-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2017-01-01	-24.4892%	2.6751%	40.381%	16.8258%	yes	2.0712%	1 / 250
2018-01-01	no segment follows this rebalance, not scored

Step 13 · 2018-01-02 → 2018-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2018-01-01	-18.2151%	0.3058%	23.4708%	-7.625%	yes	1.3816%	20 / 250
2019-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2018-01-01	-13.6349%	10.5659%	42.1749%	-12.5919%	yes	1.5372%	18 / 250
2019-01-01	no segment follows this rebalance, not scored

Step 14 · 2019-01-02 → 2019-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Projection accuracy, realized outcome fell inside the P5–P95 cone in 0.0% of 1 scored rebalances (a well-calibrated 90% band contains ~90.0%) · 95% VaR breached on 4.78% of 251 days (expected ~5.0%)

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2019-01-01	-24.6712%	-8.5612%	11.3213%	21.7253%	no	1.253%	12 / 251
2020-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2019-01-01	-18.6934%	4.1052%	33.7981%	20.3214%	yes	1.4974%	17 / 251
2020-01-01	no segment follows this rebalance, not scored

Step 15 · 2020-01-02 → 2020-12-31

Dividend yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2020-01-01	-28.9837%	-6.3684%	21.615%	-2.5176%	yes	1.8019%	57 / 252

Earnings yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2020-01-01	-22.7896%	2.707%	34.5291%	-3.9169%	yes	1.9869%	46 / 252

Step 16 · 2021-01-04 → 2021-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2021-01-01	-52.3816%	-9.3307%	74.3386%	33.5391%	yes	3.3476%	3 / 251
2022-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2021-01-01	-45.3846%	3.1463%	96.6917%	40.0012%	yes	3.5941%	0 / 251
2022-01-01	no segment follows this rebalance, not scored

Step 17 · 2022-01-03 → 2022-12-30

Dividend yield

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2022-01-01	-39.5856%	5.7766%	87.0634%	1.8943%	yes	2.9992%	6 / 250
2023-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2022-01-01	-33.5091%	16.3395%	105.6068%	-16.086%	yes	2.9223%	8 / 250
2023-01-01	no segment follows this rebalance, not scored

Step 18 · 2023-01-03 → 2023-12-29

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1% · 1 name dropped at load (28 names actually held across the window), weights renormalised onto the rest

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2023-01-01	-19.5536%	16.7117%	66.4149%	6.6636%	yes	2.1196%	4 / 176
2024-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2023-01-01	-10.662%	36.7314%	105.158%	17.6869%	yes	2.5853%	1 / 249
2024-01-01	no segment follows this rebalance, not scored

Step 19 · 2024-01-02 → 2024-12-31

Dividend yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2024-01-01	-38.4778%	-11.263%	28.7045%	15.6805%	yes	2.3717%	4 / 251

Earnings yield

Portfolio book, rebalanced annual · 1 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2024-01-01	-32.2943%	3.1401%	58.127%	19.4736%	yes	2.5699%	3 / 251

Step 20 · 2025-01-02 → 2025-12-31

Dividend yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2025-01-01	-24.9374%	0.14%	31.8132%	2.8311%	yes	1.846%	9 / 249
2026-01-01	no segment follows this rebalance, not scored

Earnings yield

Portfolio book, rebalanced annual · 2 constructions · 30 names held · selection: reselect · 0.0% in cash · turnover 1.0× · cost drag 0.1%

Rebalance	P5	Median	P95	Realized	In band	VaR 95 (1d)	Breaches
2025-01-01	-8.4885%	21.2555%	58.5741%	27.5348%	yes	1.6818%	16 / 249
2026-01-01	no segment follows this rebalance, not scored

QuanterLab · Study e936a4c583f2 · compiled August 15, 2026. Point-in-time constituents and hypothesis-registration timestamps are enforced by the platform. This report is generated from the frozen study artifact and is reproducible from the ledger above. Educational research, not investment advice: every result on this page is simulated, and nothing here is a recommendation to buy or sell any security.

Paid to wait, paid less - dividend yield against earnings yield in total returns, twenty sealed windows of the S&P 500

1 Methodology

2 Results

2.1 Headline

2.2 Per-step results

2.3 Search accounting

2.4 The comparison

3 The circuit

The objective and the search

3.1 Universe

3.2 Price Loader

3.3 Factor Loader

3.4 Factor Value

3.5 Factor Composite

3.6 Factor Top Tier

3.7 Portfolio Backtest

3.8 Portfolio Forward Autopsy

3.9 Transaction Cost

4 Projection calibration, pooled across the walk

5 Discussion

5.1 Findings

5.2 Interpretation

5.3 Limitations

References

Appendix A Reproducibility in QuanterLab

Appendix A2 Registration record

Appendix B Per-step diagnostics

Step 1 · 2006-01-03 → 2006-12-29

Step 2 · 2007-01-03 → 2007-12-31

Step 3 · 2008-01-02 → 2008-12-31

Step 4 · 2009-01-02 → 2009-12-31

Step 5 · 2010-01-04 → 2010-12-31

Step 6 · 2011-01-03 → 2011-12-30

Step 7 · 2012-01-03 → 2012-12-31

Step 8 · 2013-01-02 → 2013-12-31

Step 9 · 2014-01-02 → 2014-12-31

Step 10 · 2015-01-02 → 2015-12-31

Step 11 · 2016-01-04 → 2016-12-30

Step 12 · 2017-01-03 → 2017-12-29

Step 13 · 2018-01-02 → 2018-12-31

Step 14 · 2019-01-02 → 2019-12-31

Step 15 · 2020-01-02 → 2020-12-31

Step 16 · 2021-01-04 → 2021-12-31

Step 17 · 2022-01-03 → 2022-12-30

Step 18 · 2023-01-03 → 2023-12-29

Step 19 · 2024-01-02 → 2024-12-31

Step 20 · 2025-01-02 → 2025-12-31

Run a study like this one