What it means
Wall Street's oldest calendar advice rhymes: sell in May and go away, and stay away till St Leger Day, or Halloween, depending on which coast of the Atlantic teaches it. The claim is an anomaly: the November-through-April half of the year has historically delivered most of the stock market's return, and the summer half remarkably little.
Bouman and Jacobsen's study, The Halloween Indicator, tested the saying across dozens of countries and found the effect economically large and statistically significant in most, with returns concentrated in the winter half. The puzzle deepened rather than died: the pattern appeared in country after country, era after era, and the obvious explanations, vacation flows, earnings timing, risk variation, fit it poorly.
A calendar effect offends efficient-market instincts: if everyone knows the winter is kind, buying in October should erase the difference, yet the anomaly has outlived its publication by decades. Practical obedience carries real costs: switching twice a year incurs taxes, spreads, and the risk of missing sharp summer rallies, which is why most professionals cite the pattern and then ignore it.
The saying survives because it is half empirical regularity and half professional folklore, and separating the two is harder than the rhyme suggests. For a non-finance reader, sell in May is the market's weather proverb: the statistics say there is something in it, the theory says there should not be, and the trading costs say be careful either way.
The saying's British original ran to St Leger Day, the September horse race that marked the season when London's gentlemen returned to the City, a reminder that the anomaly may be the fossil of a social calendar. Sector and size studies add texture: the summer weakness concentrates in small and cyclical names, while defensives sleep through the calendar, which hints the effect is risk migration rather than magic.
Sceptics run the multiple-testing argument: examine enough calendars, sectors, and countries and some pattern must appear significant, so the honest reader demands out-of-sample persistence, which, unusually, this anomaly has shown.
In practice
Real-world examples.
Example
An investor's ten-year test finds the calendar edge real but a third consumed by costs and taxes. Each switch to cash triggers a taxable sale, and each return to the market means paying the spread again. The pattern survives the test, but the profit left over is much smaller than the headline figure suggested.
Example
A strategy that dodges two autumn crashes still underperforms its backtest after switching frictions. In the backtest every trade happens at the closing price with no charge, which real markets do not offer. Once commissions, spreads and delays are added, the gap between the paper result and the real one is easy to see.
Example
A professional cites the Halloween indicator in commentary and holds through the summer anyway, as most do. The reasoning is that a statistical regularity with weak theory behind it is a poor basis for abandoning a long-term allocation. The rhyme outlived the reason.
Formula
Calculation
The strategy: hold equities November through April, hold cash or reduce exposure May through October; Bouman and Jacobsen found the winter-half premium significant in most of the 37 countries tested, persisting across decades.
Worked example with invented returns. An investor starts a year with $100,000. Assume the winter half returns 6%, so the portfolio is worth 100,000 x 1.06 = $106,000.
- Poor summer: the market falls 3%. Buy-and-hold ends at 106,000 x 0.97 = $102,820. The calendar investor moves to cash earning 1% and ends at 106,000 x 1.01 = $107,060, ahead by $4,240 before costs.
- Strong summer: the market rises 4%. Buy-and-hold ends at 106,000 x 1.04 = $110,240. The calendar investor ends at $107,060, behind by $3,180.
If switching costs the investor $400 a year in spreads and fees, the poor-summer edge shrinks to 4,240 - 400 = $3,840 and the strong-summer shortfall grows to 3,180 + 400 = $3,580, before any tax on the gains. The calendar helps in some years and hurts in others.Case study
Seen in the real world.
This case study is fictional and illustrative. A made-up private investor in Dublin reads about the Halloween indicator one April and decides to test it properly: half her portfolio follows the calendar, switching to cash each May and back each November, while the other half simply holds, both tracked for ten years in a spreadsheet she updates twice a year. The decade's result is an education in anomaly economics: the calendar half finishes slightly ahead on return and noticeably ahead on smoothness, sidestepping two ugly autumn crashes, but the spreadsheet's cost column tells the quieter story, with switching fees, spreads, and taxable gains consuming a third of the edge.
The tax authority's share of the strategy bothers her most: every November purchase and May sale is a taxable event in her account type, turning a market anomaly into a revenue program for the government. Her summary for her investment club is the anomaly in one sentence: the pattern was real in my own decade, smaller than the paper promised, and expensive to obey, which is exactly what a true anomaly should look like once everyone can read about it. She keeps the calendar half running, partly for the data, mostly for the story.
Watch out
Common mistakes.
- Trading it without cost accounting; twice-yearly switching incurs taxes, spreads, and missed rallies that eat much of the historical edge.
- Treating the pattern as law; it is a statistical regularity with weak theoretical footing, and any single year can reverse it violently.
- Ignoring the publication problem; anomalies documented and popularised face decay as more money attempts to harvest them.
Questions
People also ask.
What does sell in May and go away mean?
The strategy of holding stocks from November to April and stepping aside from May to October, based on the historical winter-half return premium.
Is there evidence for it?
Bouman and Jacobsen's Halloween Indicator study found the effect significant across most countries tested, persisting long after publication, without a settled explanation.
Should investors follow it?
The raw pattern has been real, but switching costs, taxes, and missed summer rallies consume much of the edge, so most treat it as folklore with a statistical core.
From the founder's library
Take it further with the book.
Build your financial confidence beyond this definition. Shihan's full-length guide, Accounting Fundamentals, takes the same plain-English approach and turns it into a complete, practical playbook for non-finance managers, business owners and students - with chapter-end quiz answers and presentation slides included.
25% off with code MMHQ25, applied at checkout. Priced in USD - checkout may show the equivalent in your local currency.
View the book and save 25%