A regularized hidden Markov model for analyzing the ‘hot shoe’ in football

We propose a penalized likelihood approach in hidden Markov models (HMMs) to perform automated variable selection. To account for potential large number of covariates, which also may be substantially correlated, we consider the elastic net penalty containing LASSO and ridge as special cases. By quadratically approximating non-differentiable penalty, ensure that can maximized numerically. The feasibility our is assessed simulation experiments. As case study, examine ‘hot hand’ effect, whose existence highly debated different fields, such psychology economics. In present work, investigate shoe’ effect performance takers (association) football, where (latent) states HMM serve underlying form player.