Tim B. Swartz | Searcharxiv

arXiv2026

Modeling Event Dynamics by Self-Exciting Processes with Random Memory

Event history data from sports competitions have recently drawn increasing attention in sports analytics to generate data-driven strategies. Such data often exhibit self-excitation in the event occurrence and dependence within event clusters. The conventional event models based on gap times may struggle to capture those features. In particular, while consecutive events may occur within a short timeframe, the self-excitation effect caused by previous events is often transient and continues for a period of uncertain time. This paper introduces an extended Hawkes process model with random self-excitation duration to formulate the dynamics of event occurrence. We present examples of the proposed model and procedures for estimating the associated model parameters. We employ the collection of the corner kicks in the games of the 2019 regular season of the Chinese Super League to motivate and illustrate the modeling and its usefulness. We also design algorithms for simulating the event process under proposed models. The proposed approach can be adapted with little modification in many other research fields such as Criminology and Infectious Disease.

stat.ME↗

arXiv2025

Framing Causal Questions in Sports Analytics: A Tutorial on Estimand Choice Illustrated Through Crossing in Soccer

Causal inference has become an accepted analytic framework in sports analytics, where experimentation is rarely feasible. A key consideration is the choice of estimand, specifically, whether to target the Average Treatment Effect (ATE), which reflects the effect of an action across the entire population, or the Average Treatment Effect on the Treated (ATT), which reflects the effect among those who actually took the action. Using data from nearly all 240 matches of the 2019 Chinese Super League season, we apply propensity score matching to estimate the causal effect of crossing on shot creation in soccer. The ATE and ATT are nearly identical (0.033 and 0.035 respectively), a result we attribute to substantial overlap in propensity score distributions between plays where a cross was and was not attempted. To illustrate when these estimands diverge, we construct two simulation scenarios with known ground truth: one reproducing the high-overlap structure of the real data, where ATE and ATT coincide, and one engineered to exhibit severe confounding and low overlap, where they diverge substantially. While empirical findings are specific to the 2019 Chinese Super League season, the case study and simulations provide a principled guide to estimand choice in causal analyses of sports data.

stat.AP↗