Learn it → Apply it → Save as Skill
A short run of wins feels like proof that the streak will continue. Most of the time, that feeling runs far ahead of the evidence. The useful skill is checking whether a "hot" run is a real, measurable shift, or simply what ordinary chance produces.
The Dr. Wallace's Favorite Mental Models is designed to turn useful ways of thinking into reusable tools. Each model gives you a fast visual overview, deeper interactive learning, practical application exercises and an AI-ready Markdown skill you can save for future use.
Instead of merely reading about mental models, you can gradually build your own AI skills library: a collection of portable reasoning skills that can help ChatGPT, Claude, Grok and other AI assistants apply the mental models you value.
When someone succeeds several times in a row, we expect the next attempt to succeed too. In most short streaks of independent events, that expectation outruns what the numbers actually show.
Important: this up-and-down pattern is exactly what independent, randomly varying shots look like. A real "hot" shooter would need to outscore this kind of normal swing, not just show one good night.
The model is most useful when someone's run of wins or losses is about to change how much time, money, confidence or trust gets allocated next.
The method does not claim streaks are always meaningless. It asks you to check before you act on one.
Name the streak precisely: how many events in a row, over what time window, compared to what usual rate.
Work out how often a streak this long would occur by pure chance, given the normal success rate for that person, fund or process.
Check whether the streak predicts what happens next any better than the long-run average does. If the data exist, look for them rather than guessing.
Decide how much weight, if any, the streak deserves in your next allocation of money, trust, playing time or attention.
Open a use case to see what the model changes.
Check the sample size against normal variation in returns before shifting money. A short run of outperformance is common even among funds with no real edge, and most research finds limited persistence once fees and luck are accounted for.
Compare this run to that player's normal shooting percentage and typical streak lengths. Decide whether to keep feeding them the ball based on shot quality and matchup, not on the streak alone.
Look at a longer performance window and check what changed structurally (new territory, new support, easier targets) before concluding the streak reflects a permanent step up in ability.
Separate pipeline and seasonal effects from individual skill before reallocating leads or quota. A hot month inside a hot season tells you less about the person than it appears to.
In games of pure chance, past outcomes do not change future odds. Treat the urge to raise the bet "while it's working" as the bias itself, not as useful information.
Check for a specific cause (a launch, a campaign, a seasonal pattern) before briefing leadership that the trend will continue on its own.
This is an illustrative example designed to teach the method.
Expand for the actual findings behind the term, including a later correction that is often left out.
In "The Hot Hand in Basketball: On the Misperception of Random Sequences" (Cognitive Psychology, 1985), the researchers examined shot-by-shot records from the Philadelphia 76ers and a controlled shooting study with Cornell players. They found that whether a player had made or missed their previous shots did not meaningfully predict whether the next shot went in, even though players and fans strongly believed otherwise.
Not quite, and later work changed the picture. The 1985 result was widely summarized as "the hot hand is a myth," which overstated the finding. The careful claim was narrower: in the data examined, the belief in streaks was far stronger than any real pattern the data could support.
Joshua Miller and Carlos Sanjurjo (2015 working paper, formally published 2018 in Econometrica) identified a subtle selection bias in how the original studies and similar ones measured streaks in finite sequences, one that mechanically understates any real hot-hand effect. Correcting for it, they found a small but genuine hot-hand effect in some of the same data, including a reanalysis of the original 1985 study and NBA three-point contest shooting. The effect was real but considerably smaller than the popular belief in "hot streaks," which is the nuance this model is built around.
A dramatic streak is easy to recall and feels common. Compare it to how often streaks of that length actually occur, not to how vivid it felt.
Ten shots, three quarters, or four hands is rarely enough data to distinguish a real shift from ordinary variation.
Performance that is unusually high tends to drift back toward the average next period, with or without a lasting cause.
Rotating money toward whatever just outperformed is one of the most costly real-world versions of this bias.
Dismissing every streak as "just noise" can miss real, measurable changes, such as an injury healing or a genuine swing change. Test; do not assume either direction.
there is a known mechanism: a recovered injury, a coaching change, new equipment, or a documented change in process.
the stakes are high enough (a hiring decision, a large reallocation of capital) to justify a proper test for serial dependence rather than a judgment call.
you are tempted to label every streak "just chance" and ignore evidence of genuine, sustained improvement.
This browser tool structures your thinking. It does not send your information anywhere or perform AI analysis.
Save as Skill converts the model into portable Markdown instructions that teach an AI when and how to apply the Hot-Hand Fallacy, what questions to ask, what evidence to seek, what mistakes to avoid and how to structure its analysis.
Save the skills you find useful and organize them into your own reusable library. The Markdown is intentionally model-neutral, so it can be used wherever an AI system accepts uploaded files, project knowledge, custom instructions or reusable text context. Platform capabilities differ, so this is a portable skill file rather than a claim of one-click installation.
Sometimes. If a streak coincides with a real, checkable cause, such as a recovered injury, a new technique, or a genuine change in conditions, that cause (not the streak length itself) is what should carry weight in a decision.
Both misjudge independent or near-independent events. The Gambler's Fallacy expects a streak to reverse ("red has come up five times, black is due"). The Hot-Hand Fallacy expects a streak to continue ("she's made five in a row, she won't miss"). They are opposite errors about the same kind of evidence.
Small. In their reanalysis, the corrected hot-hand effect in shooting data was real but modest, nowhere near large enough to justify the strength of belief most players, coaches and fans place in a "hot" streak. The honest takeaway is "smaller than you think, not zero."