Ensemble Learning with Recursive Partitioning Methods to Explore Relationships between Mental Health and Physical Activity

Author

Jessica GilmoreFollow

Date of Graduation

12-2020

Document Type

Thesis

Degree Name

Bachelor of Science

Degree Level

Undergraduate

Department

Health, Human Performance and Recreation

Advisor/Mentor

Robinson, Samantha

Committee Member/Reader

Hickey, Erin

Abstract

Physical and mental health are imperative to maintaining a well functioning immune system, which is especially critical during a global pandemic. Moreover, physical and mental health contribute to the overall quality of life experienced by an individual. Consequently, it is important to explore factors that contribute to both physical and mental health. Physical activity has been previously shown to improve physical and mental health yet many individuals do not get enough physical activity daily. Using data collected during the larger Exercise is Medicine (EIM) study, the current study utilized ensemble learning with recursive partitioning methods to explore the relationships that exist between health as measured by the SF-12, various types of physical activity as measured by the International Physical Activity Questionnaire (IPAQ), and participant demographics. Results indicated that physical activity, especially in leisure, is an important variable contributing to both physical and mental health. Results also demonstrated the value in utilizing ensemble learning with recursive partitioning methods to study the effect of physical activity on overall health.

Citation

Gilmore, J. (2020). Ensemble Learning with Recursive Partitioning Methods to Explore Relationships between Mental Health and Physical Activity. Health, Human Performance and Recreation Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/hhpruht/92