B1809
Title: Flexible cost-penalized Bayesian model selection: Developing inclusion paths with application to medical diagnoses
Authors: Christopher Franck - Virginia Tech (United States)
Erica Porter - Clemson University (United States) [presenting]
Stephen Adams - Virginia Tech National Security Institute (United States)
Abstract: A Bayesian model selection approach is proposed that allows medical practitioners to select among predictor variables while taking their respective costs into account. Medical procedures almost always incur costs in time and/or money. These costs might exceed their usefulness for modeling the outcome of interest. Bayesian model selection is developed that uses flexible model priors to penalize costly predictors a priori and select a subset of predictors useful relative to their costs. The approach (i) gives the practitioner control over the magnitude of cost penalization, (ii) enables the prior to scale well with sample size, and (iii) enables the creation of the proposed inclusion path visualization, which can be used to make decisions about individual candidate predictors using both probabilistic and visual tools. The effectiveness of the inclusion path approach is demonstrated, as well as the importance of being able to adjust the magnitude of the priors cost penalization through a dataset pertaining to heart disease diagnosis in patients at the Cleveland clinic foundation, where several candidate predictors with various costs were recorded for patients, and through simulated data.
