Poster Presented by Ihnwhi Heo and Mercedes Peña
Heo, I., Peña, M., Depaoli, S., Prather, A., Epel, E., & Zawadzki, M. J. (2026, April 22-25). Keep calm and drop out? Predicting attrition in an mHealth meditation app using Bayesian model averaged logistic regression [Poster presentation]. Society of Behavioral Medicine, Chicago, IL, USA
Using Bayesian model averaging, we identified meditation group assignment and income level as the strongest predictors of attrition in a Headspace mindfulness intervention. Specifically, meditation group participants were 38% more likely to drop out, while middle-to-high income individuals were 36-39% less likely, highlighting key targets for retention strategies.
Poster Presented by Mercedes Peña
Peña, M., Heo, I., Depaoli, S., & Zawadzki, M. J. (2026, April 22-25). Identifying screening-level predictors of enrollment in a mobile mindfulness RCT using Headspace: A Bayesian model-averaged logistic regression approach [Poster presentation]. Society of Behavioral Medicine, Chicago, IL, USA.
Using Bayesian model averaging, we identified meditation experience, having children, and income level as key predictors of enrollment in a mobile mindfulness RCT. Specifically, individuals with meditation experience were 4.5 times more likely to enroll and those with children were 2.5 times more likely, whereas the lowest-income group was less likely to enroll, highlighting important targets for recruitment strategies.