The role of intrinsic dimension in high-resolution player tracking data -- insights in basketball

DOI10.1214/21-AOAS1506zbMath1498.62350arXiv2002.04148OpenAlexW3005701371WikidataQ114599233 ScholiaQ114599233MaRDI QIDQ2135355

Francesco Denti, Antonietta Mira, Kerrie L. Mengersen, Edgar Santos-Fernández

Publication date: 6 May 2022

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.04148

zbMATH Keywords

intrinsic dimensionhigh-dimensional dataBayesian clusteringmovement dataplays classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Pattern recognition, speech recognition (68T10) Applications of statistics (62P99)

Uses Software

• ggplot2
• tidyverse
• Superheat
• mcclust
• ggrepel
• gganimate

Cites Work

• Unnamed Item
• Unnamed Item
• Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
• Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems
• Bayesian cluster analysis: point estimation and credible balls (with discussion)
• Intrinsic dimension estimation: relevant techniques and a benchmark framework
• Intrinsic dimension estimation: advances and open problems
• Panel data analysis: a survey on model-based clustering of time series
• Novel high intrinsic dimensionality estimators
• New formulation of the logistic-Gaussian process to analyze trajectory tracking data
• Characterizing the spatial structure of defensive skill in professional basketball
• Bayesian Density Estimation and Inference Using Mixtures
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• The intrinsic dimensionality of signal collections