Multiple Time Scale Models in Sport and Exercise Science
Date of Original Version
In sport and exercise research, examining both within- and between-individual variation is crucial. The ability to investigate change both within competitive events and across a competitive season is a priority for many sport researchers. The aim of this article is to demonstrate an approach to analyzing intensive longitudinal data collected through time-scale-dependent longitudinal designs. Following didactic presentation of the approach, two illustrations from secondary data analysis are used to describe the modeling process in detail. Illustration 1 includes affective response data from an exercise intervention randomized pilot study. Illustration 2 uses referee and player distance data collected during professional soccer games in the English Premier League. Each illustration describes a process for testing and comparing multiple time scale models based on the three-level multilevel model, and results are interpreted. In the discussion, advantages and limitations of the approach are highlighted.
Measurement in Physical Education and Exercise Science
Smith, Daniel M., and Theodore A. Walls. "Multiple Time Scale Models in Sport and Exercise Science." Measurement in Physical Education and Exercise Science 20, 4 (2016): 185-199. doi:10.1080/1091367X.2016.1195390.