Event

Variable selection is a common problem in regression modelling with a myriad of applications. This talk will present a new feature ranking algorithm (DEPTH) for variable selection in parametric regression based on permutation statistics and stability selection. DEPTH is: (i) applicable to any parametric regression model, (ii) designed to be run in a parallel environment, and (iii) adapts naturally to the correlation structure of the predictors. The empirical performance of DEPTH will then be discussed with application to a genome-wide association study of breast cancer. Here, DEPTH found evidence that there are variants in a pathway of candidate genes that are associated with a common sub-type of breast cancer, a finding which would not have been discovered by conventional analyses.