Bayesian Variable Selection with Applications in Health Sciences

In health sciences, identifying the leading causes that govern behaviour of a response variable is question crucial interest. Formally, this can be formulated as selection problem. paper, we introduce basic concepts Bayesian approach for based on model choice, emphasizing space prior adoption and algorithms sampling from posterior probabilities approximation; show its application to two common problems in sciences. The first concerns problem field genetics while second longitudinal study cardiology. context these applications, considerations about control multiplicity via distribution over space, linear models which number covariates exceed sample size, with censored data, computational aspects are discussed. applications presented here also have an intrinsic statistical interest proposed go beyond standard general model. We believe work will broaden access practitioners methods selection.