Chart patterns and candlestick setups
Does 'holding above the midpoint' confirm a move?
Rejected Pre-registered and tested, July 2026
The setups the midpoint rule eliminates did better than the setups it approves.
What the pattern claims
Deliberately not a breakout test. A big green candle appears on heavy volume, closing strongly. Price then pulls back over the following sessions but holds above the halfway point of that candle. A close below the midpoint cancels the setup entirely. The claim is that holding the midpoint shows the move was accumulation rather than a spike.
How we tested it
3,589 occurrences on S&P 500 companies, well powered, with the candle-size definition reused verbatim from an earlier study so it was not a fresh parameter to tune.
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
−1.05% at 60 days over the full period; −0.84% in the first era and −2.03% in the second. It failed all six of its pre-registered criteria and beat none of its four placebos.
The load-bearing number is the comparison within the setup. Of 5,774 occurrences, the rule keeps 3,640 and discards 2,134. Those two groups add up exactly, so nothing is being selected between them.
The kept group returned −1.05%. The discarded group — the ones that broke the midpoint — returned −0.19%, beating them by 0.86 percentage points. In the second era the discarded group was actually positive while the kept group lost 2%.
What it means
Because both arms come from the same pool of occurrences, this cannot be explained by the setups firing on different days or in different market conditions. It is a like-for-like comparison, and the rule picked the worse half.
The same shape appeared in the breakout-and-retest study, on a different construction and a different set of companies. Two independent tests of 'the level held, so the move is confirmed' both found that the setups where the level broke did better. At that point it stops being a curiosity about one pattern and becomes a property of the family.
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.