Date of Award

5-2026

Document Type

Thesis

Degree Name

Bachelor of Arts (BA)

Department

Natural Sciences

First Advisor

Skripnikov, Andrey

Area of Concentration

Data Science

Abstract

This thesis develops a survival analysis framework for modeling career longevity and exit risk for specifically position players in Major League Baseball using historical player performance and injury data. Utilizing longitudinal player-season observations from the Lahman Baseball Database alongside external injury and retirement records, the study constructs a time-to-event modeling framework centered around the Cox proportional hazards model with time-varying covariates. Offensive performance metrics, aging effects, workload measures, missed-season indicators, and injury severity variables are incorporated to evaluate how player characteristics influence the likelihood of MLB career continuation. To account for nonlinear aging and performance relationships, natural spline transformations and interaction effects are introduced throughout the modeling process. Multiple model specifications are evaluated using Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and concordance index (C-index) comparisons to balance statistical fit and predictive discrimination. Results indicate that age, recent offensive production, playing opportunity, injury accumulation, and missed-season continuity all significantly influence career survival patterns. In particular, plate appearances emerge as one of the strongest predictors of continued career stability, while interrupted playing continuity substantially increases projected exit risk. Beyond predictive modeling, the thesis also explores projected career trajectories through player-specific case studies representing star players, injury-shortened careers, average career paths, and short-duration MLB careers. Overall, the study demonstrates how survival analysis can provide an interpretable and flexible framework for understanding career sustainability, aging induced decline, and organizational value within professional baseball. **Portions of the coding workflow, formatting refinement, and editorial wording assistance for this thesis were supported through the use of OpenAI’s ChatGPT language model.**

Rights

The author has granted New College of Florida the nonexclusive right to archive, make accessible, and distribute for educational purposes this work in whole or in part in all forms of media, now or hereafter known. The copyright of this work remains with the author.

Download

Share

COinS