2020/05/18 by Erin M. Schliep, Schliep, Erin M., Toryn L. J. Schafer +3
Economics, Econometrics and Finance · Medicine · #Applications (stat.AP) #FOS: Computer and information sciences #Sports Analytics and Performance #Sports Performance and Training #Sports injuries and prevention
paper · pdf · doi:10.48550/arxiv.2005.09024
openalex publication_date 2020/05/18 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Subjective wellness data can provide important information on the well-being\nof athletes and be used to maximize player performance and detect and prevent\nagainst injury. Wellness data, which are often ordinal and multivariate,\ninclude metrics relating to the physical, mental, and emotional status of the\nathlete. Training and recovery can have significant short- and long-term\neffects on athlete wellness, and these effects can vary across individual. We\ndevelop a joint multivariate latent factor model for ordinal response data to\ninvestigate the effects of training and recovery on athlete wellness. We use a\nlatent factor distributed lag model to capture the cumulative effects of\ntraining and recovery through time. Current efforts using subjective wellness\ndata have averaged over these metrics to create a univariate summary of\nwellness, however this approach can mask important information in the data. Our\nmultivariate model leverages each ordinal variable and can be used to identify\nthe relative importance of each in monitoring athlete wellness. The model is\napplied to athlete daily wellness, training, and recovery data collected across\ntwo Major League Soccer seasons.\n