Clustered data in sports research

SummaryClustered, or dependent, data, arise commonly in sports medicine and sports science research, particularly in studies of sports injury and biomechanics, particularly in sports injury trials that are randomised at team or club level, in cross-sectional surveys in which groups of individuals are studied and in studies with repeated measures designs. Clustering, or positive correlation among responses, arises because responses and outcomes from the same cluster will usually be more similar than from different clusters. Study designs with clustering will usually required an increased sample size when compared to those without clustering. Ignoring clustering in statistical analyses can also lead to misleading conclusions, including incorrect confidence intervals and p-values. Appropriate statistical analyses for clustered data must be adopted. This paper gives some examples of clustered data and discusses the implications of clustering on the design and analysis of studies in sports medicine and sports science research.