View in EDS

Functional Data Analysis of the Power–Duration Relationship in Cyclists.

Saved in:
Bibliographic Details
Title: Functional Data Analysis of the Power–Duration Relationship in Cyclists.
Authors: Puchowicz, Michael J., Skiba, Philip F.
Source: International Journal of Sports Physiology & Performance; Oct2025, Vol. 20 Issue 10, p1331-1340, 10p
Subject Terms: PEARSON correlation (Statistics), PREDICTION models, DATA analysis, SCIENTIFIC observation, DESCRIPTIVE statistics, CYCLING, STATISTICS, RESEARCH methodology, PHYSICAL fitness, ATHLETIC ability, EXERCISE tests, FACTOR analysis, DATA analysis software, SENSITIVITY & specificity (Statistics), SPRINTING
Abstract: Purpose: To extract, prioritize, and model the highly conserved variations in mean-maximal power (MMP) data in cyclists utilizing functional principal component (FPC) analysis. Methods: A 3-parameter model (F3 model) was derived from the first 3 functions identified by FPC analysis of a large MMP data set. The F3 model was assessed for goodness of fit to a reserved out-of-sample partition of the MMP data set. Post hoc external validation was used to test the sensitivity of the second FPC to sprint and endurance bias within published data. Results: The first 3 FPCs accounted for 97% of the variation in the MMP data. The FPCs were interpretable as gain, sprint–endurance bias, and W′ analog functions, respectively. The F3 model showed excellent out-of-sample goodness of fit. FPC2 discriminated between sprint- and endurance-biased data in a post hoc analysis. Conclusion: FPC analysis is a powerful tool to statistically identify functions that describe the principal modes of variation in MMP data. The identified functions and resulting F3 model show great promise for performance prediction, as well as revealing novel insights into the mechanistic determinants of exercise performance. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Sports Physiology & Performance is the property of Human Kinetics Publishers, Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:Purpose: To extract, prioritize, and model the highly conserved variations in mean-maximal power (MMP) data in cyclists utilizing functional principal component (FPC) analysis. Methods: A 3-parameter model (F3 model) was derived from the first 3 functions identified by FPC analysis of a large MMP data set. The F3 model was assessed for goodness of fit to a reserved out-of-sample partition of the MMP data set. Post hoc external validation was used to test the sensitivity of the second FPC to sprint and endurance bias within published data. Results: The first 3 FPCs accounted for 97% of the variation in the MMP data. The FPCs were interpretable as gain, sprint–endurance bias, and W′ analog functions, respectively. The F3 model showed excellent out-of-sample goodness of fit. FPC2 discriminated between sprint- and endurance-biased data in a post hoc analysis. Conclusion: FPC analysis is a powerful tool to statistically identify functions that describe the principal modes of variation in MMP data. The identified functions and resulting F3 model show great promise for performance prediction, as well as revealing novel insights into the mechanistic determinants of exercise performance. [ABSTRACT FROM AUTHOR]
ISSN:15550265
DOI:10.1123/ijspp.2024-0548