The turn of the month: most of the stock market's rise would come between the last trading day of a month and the third of the next, when wages and pension contributions flow in.
A much higher return per invested day around the turn of the month. Not a higher total return than buy-and-hold.
| Market | Unseen period | Verdict | Rule / buy-and-hold | Max drawdown rule / buy-and-hold | Proof |
|---|---|---|---|---|---|
| Asia-Pacific ex Japan | 2008-05 → 2026-08 (18.3 y) | No proof of an edge yet | +3.4% / +153.4% | 33.1% / 59.4% | SAP-ca9be788f6f8 |
| Europe | 2008-05 → 2026-08 (18.3 y) | No proof of an edge (a loss on the unseen period) | -13.7% / +163.4% | 37.3% / 60.0% | SAP-4a7e5be91e5b |
| Japan | 2008-05 → 2026-08 (18.3 y) | No proof of an edge (a loss on the unseen period; Deflated Sharpe below 50%) | -53.2% / +216.2% | 59.8% / 45.3% | SAP-8b34bb10f4c1 |
| United States | 2008-05 → 2026-08 (18.3 y) | No proof of an edge yet | +5.0% / +687.1% | 18.0% / 50.7% | SAP-6bcca42a70a3 |
What the theory brings, measured. Invested about 19% of days, the turn-of-the-month rule earned +5.0% in the US over 18.3 unseen years, vs +687.1% for buy-and-hold, and it loses in Europe and Japan. The effect described in 1987 and confirmed in 2008 does not show up after those publications, fees included. A useful measure: a famous calendar effect can fade once known (McLean and Pontiff, 2016). Note: the rule reads the calendar of coming sessions (declared in the record); the Lab's leak check flags it, and the conclusion does not depend on it.
Rule written and preregistered on 12/10/2026, before any proof, with its source's parameters; one trial per market, nothing tuned; judged in certified mode by Lab 270, which cuts the unseen period itself: everything after the source's publication. "Rule / buy-and-hold": gain of the rule and of buy-and-hold on the same bars, 10 bp fee per order. Proofs SAP-ca9be788f6f8, SAP-4a7e5be91e5b, SAP-8b34bb10f4c1, SAP-6bcca42a70a3. Gaps with the source: Buy at the close of day −2 to earn day −1; US trading calendar for every region; the rule reads the calendar of coming sessions (known in advance, declared). Data: Ken French Data Library, FRED (Board of Governors). Research on past data, not advice; no future return is promised.
Ariel, R. A. (1987), "A monthly effect in stock returns", JFE 18(1), 161-174, DOI 10.1016/0304-405X(87)90066-3; Lakonishok, J., Smidt, S. (1988), RFS 1(4), 403-425, DOI 10.1093/rfs/1.4.403; McConnell, J. J., Xu, W. (2008), FAJ 64(2), 49-64, DOI 10.2469/faj.v64.n2.11.