Abstract
Introduction: The relationship between training loads and injuries has been studied extensively in sports medicine. Transforming continuous risk factors (such as cumulative load or the acute:chronic workload ratio) into discrete or categorical variables has been a common methodological approach. Discretisation of continuous variables can have significant negative impacts on statistical power, estimated effects and false positive rates. This study presents the limitations of some common modelling strategies and provides improved alternatives.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have