Available at: https://digitalcommons.calpoly.edu/theses/3298
Date of Award
6-2026
Degree Name
MS in Statistics
Department/Program
Statistics
College
College of Science and Mathematics
Advisor
Kevin Ross
Advisor Department
Statistics
Advisor College
College of Science and Mathematics
Abstract
The hot-hand phenomenon, often described as the tendency for individuals to experience prolonged streaks of success that exceed what would be expected under random performance, has been widely studied across many disciplines, particularly basketball. Early studies attempted to evaluate this effect through various techniques, often concluding that the hot-hand phenomenon was largely a myth. However, recent studies have begun to revisit previous analyses using improved statistical techniques, with some claiming evidence of a discernible hot-hand effect. This study examines the presence of the hot-hand effect in the modern NBA by testing whether observed shooting patterns deviate from those simulated under independence. A permutation-based analysis, which preserves observed shot outcomes while randomizing order, reveals that the observed shot sequences generally do not exhibit elevated streak behavior, providing limited evidence of a hot-hand effect beyond what would be expected by chance. To further account for player and season-level heterogeneity, a logistic hierarchical model was constructed to control for in-game variables that contribute to shot success. The estimated effects of being in a hot state are small and reinforce the findings of the permutation test after adjusting for additional covariates.