Back

Did a true change occur? Improving analytical decisions for serial performance testing in sport.

Ward, P.; Morrison, S.; Bullock, G. S.

2025-09-27 sports medicine
10.1101/2025.09.22.25336149 medRxiv
Show abstract

Monitoring strategies are used to assess athletes physical readiness to maximize performance. These data are used to assist practitioners and coaches in making decisions about the volume and intensity of the upcoming training, practice, and competition. Often, these measurements are serial in nature, where the athlete is evaluated for longitudinal changes over the course of a competitive season. The target of these strategies is commonly directed at determining whether the athlete has recovered from the most frequent bout of training or competition or adapted to the current training. Sport scientists seek to identify individualized athlete changes from serial measurements to understand how the athlete is responding to their training and competitive demands to optimize performance. Within this paper, we demonstrate novel individualistic probabilistic Bayesian methods that improve analytical based decisions concerning true athletic changes during serial (i.e., repeated) measures. We then discuss practical examples, providing open access computer code and data, to assist the practitioner in creating future scalable resources.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.