Missing data patterns in runners’ careers: do they matter?

Abstract

Predicting the future performance of young runners is an important research issue in experimental sports science and performance analysis. We analyse a dataset with annual seasonal best performances of male middle distance runners for a period of 14 years and provide a modelling framework that accounts for both the fact that each runner has typically run in 3 distance events (800, 1,500, and 5,000 m) and the presence of periods of no running activities. We propose a latent class matrix-variate state space model and we empirically demonstrate that accounting for missing data patterns in runners’ careers improves the out of sample prediction of their performances over time. In particular, we demonstrate that for this analysis, the missing data patterns provide valuable information for the prediction of runner’s performance.

Filling the gaps: A multiple imputation approach to estimating aging curves in baseball

“…Recently, researchers have noticed the benefits of accounting for missing data in modeling performance in sports. Stival et al (2023) used a latent class matrixvariate state-space framework to analyze runners' careers, and found that missing data patterns greatly contribute to the prediction of performance. Perhaps the most closely related approach to our work is that by Schuckers et al (2023), which considered different regression and imputation frameworks for estimating the aging curves in the National Hockey League (NHL).…”