Synthetic Data for Sharing and Exploration in High-Performance Sport: Considerations for Application

BackgroundSynthetic data represent alternative data sources generated using mathematical procedures to address specific issues in research and practice. Synthetic data have emerging applications in clinical and medical data contexts and may assist in overcoming privacy issues to help support open science practice.ObjectiveThe present study discusses the applicability of an established synthetic data generation process using sequential tree-based algorithms (synthpop package in R) in the context of athlete monitoring data in sport, with the aim of providing an educational primer and discussion for potential application of these methods when exploring issues in the field sports and exercise sciences.MethodsThe software package in R, synthpop, was used in seven simulation conditions applied to a professional football dataset, with varying model constraints. Classification and regression trees were used as the base model framework for each simulation. Metrics associated with both global utility (overall dataset similarity) and specific utility (specific research outcome similarity) were assessed on each simulation condition.ResultsAll simulation conditions demonstrated high levels of global utility. Additionally, simpler simulation conditions, which more closely resembled the analysis of the original dataset (simulation condition 1 and 2), provided higher specific utility than more advanced simulation conditions.ConclusionTo summarize, three types of models can be conceptualised for generating synthetic data: (1) models used for analysis of the original data (answering specific research questions), (2) models used to generate synthetic data, and (3) models that represent the true generation process for the original data. Misalignments in the specifications of these models might introduce biases that can compromise the utility of synthetic data no matter the purpose. As synthetic data do not constitute a direct replacement for real data from conceptual and empirical standpoints, we believe that researchers embracing this practice must include sufficient documentation concerning the synthetic data generation process purpose, the predictors and model used, and the potential boundary conditions for using the synthetic data in future investigations in sports and other fields.