|
Abstract:
|
Ecological statistics is an exciting field of research due to the challenges posed by high-dimensional environmental processes with complex dependencies. As statisticians, we are continuously tasked to develop advanced statistical methods and models that account for these complex dependences to make informed inference and prediction in the presence of uncertainty. Interestingly, the novel insights provided by these methods extend well beyond the world of ecology. We demonstrate the scope of these methods by combining various statistical approaches that have been developed for (or are commonly used in) ecological applications to study the cumulative effects of training and recovery in athletes. In particular, our approach leverages methods for multivariate and ordinal data, as well as latent factor models and distributed lag models, for which the recent "ecological memory models" are a special case. The model is applied to athlete daily wellness, training, and recovery data collected across two Major League Soccer seasons.
|
