Date

2-29-2024

Department

School of Health Sciences

Degree

Doctor of Philosophy

Chair

Jon Davis

Keywords

External Workload, Sports Science, Strength and Conditioning, Workload Management, Multivariate Statistics

Disciplines

Health and Physical Education | Kinesiology

Abstract

The worlds of sports science, data analytics, and sports performance are at a crossroads. Each field is accustomed to functioning in relative silos; however, this approach is quickly becoming outdated. Sporting organizations are adopting high-performance models that integrate all departments and their subsequent data pipelines. This has led to a wealth of information not available before to a team’s performance health staff in guiding optimal athletic performance. Within the sport of basketball, these silos can be split further into video coaching, basketball analytics, sports science, player development, and performance health. Specifically, basketball sports science can be categorized into internal and external workloads. Internal workload measures variables like heart rate (max, average), heart rate variability (HRV), and sleep scores. External workload can be measured using force plates, isometric strength testing, and local positioning systems (LPS). LPS systems provide a wide variety of metrics which can exceed 100 variables per player and per game. This can make data aggregation difficult and overwhelming, causing a hinderance in coaching decisions. Thus, this study used a principal component analysis (PCA) to reduce the dimensions of an LPS system on external workload. All 82 games from the 2022-2023 regular NBA season were used for this project. A PCA with corresponding measures of sphericity and collinearity was conducted using Statistical Package for the Social Sciences (SPSS). The results of this study will help clinicians and practitioners be able to understand which post-game variables are important to make decisions in guiding recovery and promoting optimal court performance.

Download

Share

COinS