Chart patterns and candlestick setups
Does buying stocks that close at the day's high work?
Rejected Pre-registered and tested, August 2026
Stocks closing at the day's low beat stocks closing at the day's high, by a small but real margin.
What the pattern claims
A stock that closes right at the top of its daily range, on expanding volume, is finishing the day under buying pressure. The claim is that the pressure carries overnight: buy the close, sell the next morning's open.
How we tested it
189,000 occurrences. Unusually for this family, a single-session test rather than a multi-week one.
Every study here was pre-registered: the exact rule, the pass and fail thresholds and the data window were written down and cryptographically fingerprinted before the test was run. That makes it impossible to move the goalposts after seeing the answer.
Results assume you buy at the next morning's open, not at the closing price that triggered the signal, and they include companies that were later delisted or went bust. Returns are measured against what the rest of the market did on the same days, so a rule that made money only because it fired on days everything rose scores zero here.
What happened
The clause inverted. Buying stocks that closed in the top 15% of their range returned −0.0296% per night. Buying stocks that closed in the bottom 15% returned +0.0233%. Closing at the low beat closing at the high by 0.053 percentage points a night — the opposite of the hypothesis, and with enough occurrences behind it to be real rather than noise.
What it means
There is a genuine overnight anomaly here, and it is worth being precise about why it still does not help you. Across 3.6 million observations, the average stock gains +0.067% between the close and the next open. That is real and it is large relative to a single session.
But it is something the whole market does on the same nights. Any random basket of stocks collects it for free. It is a fact about those nights, not about the stocks you picked, which is why subtracting what the market did is mandatory here rather than a nicety.
And it funds nothing. Holding overnight and selling at the open is 252 round trips a year. At roughly 0.44% per round trip in costs, the anomaly is consumed many times over before you see any of it.
This study also settled a doubt about the other thirteen. Every previous inverted clause had been on a multi-week horizon, so the inversions could conceivably have been an artefact of long holding periods. This one inverted overnight, on a different mechanism, with a real underlying effect. The pattern holds regardless of horizon.
A rejection is not "this never works"
It means: tested on this universe, over this period, against a bar written down in advance, it did not clear the bar. Where a test lacked the power to decide either way we record it as undecided rather than rejected. The full research ledger has all 192 experiments and what the failures have in common.
Other patterns we tested
- Does the bull flag pattern work? The pole is the only live part of the pattern. Every flag condition made the result worse.
- Does MACD divergence work? The loose version changed the outcome by less than one hundredth of a percent. The strict version widened both tails.
- Does breakout and retest work? The setups the rule throws away outperformed the ones it keeps.
- Does buying the dip after a spike work? The first pattern in this family to lose money significantly rather than merely do nothing.
- Does a big RSI drop mark a buying opportunity? The family's only statistically significant result, and it vanished completely once we accounted for when it fired.
- Do three shrinking red candles signal a bottom? The only chart pattern that beat all its own control groups — and it still could not clear the error bars.