ORCID

0000-0003-2758-1143

Date of Award

2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Complex Systems and Data Science

First Advisor

Brittany M. Williams

Abstract

Through three connected studies, this research examined the complex relationship between lifestyle behaviors and mental health outcomes among college students at doctoral universities using data from the Healthy Minds Study (2021-2022). The first study (N = 12,041) used multiple linear regression analysis to examine relationships between lifestyle behaviors and mental health outcomes, revealing that physical activity is a strong protective factor against anxiety and depression. In contrast, insufficient sleep, excessive sleep, and substance use were associated with poorer outcomes. The second study (N = 8,961) used cluster analysis to identify distinct behavioral patterns, revealing two clusters primarily differentiated by substance use, with demographic factors significantly influencing cluster membership. Compared to students in the higher substance use cluster, students in the lower substance use cluster reported lower anxiety and depression scores. The third study (N = 6,865) evaluated five statistical learning algorithms for mental health classification, achieving accuracy rates of 75% for anxiety and 78% for depression. Across all three studies, contextual factors such as loneliness, a sense of belonging, and financial stress emerged as crucial predictors of mental health outcomes, substantially improving model performance when included. These studies collectively provide a comprehensive framework for understanding student mental health, suggesting that effective interventions must address both individual behaviors and broader social determinants of health in university settings.

Language

en

Number of Pages

264 p.

Available for download on Wednesday, April 29, 2026

Share

COinS