Related Experiment Video
Updated: May 1, 2026
04:13
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
Published on: February 8, 2019
5.9K
Bayesian latent structure modeling of walking behavior in a physical activity intervention
Andrew B Lawson1, Caitlyn Ellerbe2, Rachel Carroll2
1Division of Biostatistics, Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, USA lawsonab@musc.edu.
Statistical Methods in Medical Research
|April 18, 2014
Summary
This study introduces a Bayesian model to analyze walking behavior in physical activity interventions, accounting for participant ability, willingness, and dropout. The model helps understand factors influencing walking propensity and intervention effectiveness.
Area of Science:
- Behavioral Science
- Statistical Modeling
- Public Health Interventions
Background:
- Understanding physical activity behavior is crucial for public health.
- Participant dropout is a common challenge in intervention studies.
- Existing models may not fully capture the complexities of walking behavior.
Purpose of the Study:
- To propose a Bayesian latent structure modeling approach for analyzing walking behavior.
- To jointly model participant ability, willingness, and dropout processes.
- To evaluate the influence of socio-psychological and spatial predictors on walking behavior.
Main Methods:
- Bayesian latent structure modeling
- Linked survival model for dropout analysis
- Posterior sampling for computational efficiency
- Simulated evaluation of model performance
Main Results:
- The proposed model can recover latent structures and predictor effects.
- Socio-psychological and spatial neighborhood factors influence walking propensity.
- These factors also impact the estimation of latent ability and willingness.
Conclusions:
- The Bayesian latent structure model provides a robust framework for analyzing complex walking behaviors.
- Understanding participant ability, willingness, and dropout is key to effective physical activity interventions.
- Neighborhood and individual factors play significant roles in promoting walking behavior.
