Functional Concurrent Regression Mixture Models Using Spiked Ewens-Pitman Attraction Priors

Functional concurrent, or varying-coefficient, regression models are a form of functional data analysis methods in which covariates and outcomes collected concurrently. Two active areas research for this class identifying influential clustering their relations across observations. In various applications, researchers have applied developed to address these objectives separately. However, no approach currently performs both tasks simultaneously. paper, we propose fully Bayesian concurrent mixture model that simultaneously variable selection subject-specific trajectories. Our introduces novel spiked Ewens-Pitman attraction prior identifies clusters subjects’ trajectories marginally each covariate while using similarities auxiliary patterns inform allocation. Using simulated data, evaluate the clustering, selection, parameter estimation performance our compare its with alternative processes. We then apply method novel, smartphone-based smoking cessation intervention study investigate individual-level dynamic between behaviors potential risk factors.