The 'hot hand' in basketball is a myth — streaks are just chance.
Verdict: mixed
The famous debunking contained a subtle statistical bias; corrected, a small real hot hand reappears.
What the evidence shows
Gilovich, Vallone & Tversky (1985) analysed shooting data and concluded the 'hot hand' — the belief that making shots makes the next more likely — was a cognitive illusion; makes and misses looked essentially random. For decades this was the textbook example of humans seeing patterns in noise.
Miller & Sanjurjo (2018) uncovered a subtle bias in the original method: when you select the shots that follow a streak of hits from a finite sequence, pure chance already makes the follow-up hit-rate appear lower than the base rate. Correcting for this, the data actually show a small but genuine hot-hand effect. So the strong 'it's pure superstition' claim is not right; a modest hot hand exists — but it is far smaller than fans believe, so both the debunkers and the true believers were partly wrong.
Sources
Gilovich, T., Vallone, R., & Tversky, A. (1985). The hot hand in basketball: On the misperception of random sequences.
Cognitive Psychology, 17(3), 295–314
Found no evidence that a made shot raised the chance of the next, concluding the hot hand was an illusion.
DOI: 10.1016/0010-0285(85)90010-6 →Miller, J. B., & Sanjurjo, A. (2018). Surprised by the hot hand fallacy? A truth in the law of small numbers.
Econometrica, 86(6), 2019–2047
Identified a selection bias in the original analysis; correcting it reveals a small but real hot-hand effect.
DOI: 10.3982/ECTA14943 →