Ryan J. Urbanowicz

Statistical Inference Relief (STIR) feature selection

The paper introduces STIR, a statistical inferential framework for Relief-based feature selection that accounts for variance in nearest neighbor distances to assess feature importance and significance in high-dimensional data.

Collective feature selection to identify crucial epistatic variants

The paper introduces a collective feature selection approach to identify epistatic variants by combining multiple methods, showing improved performance in detecting true positive interactions in both simulated and real BMI data.