A0475
Title: On sparse directional regression
Authors: Gayun Kwon - Ewha Womans University (Korea, South) [presenting]
Abstract: Sufficient dimension reduction has developed as a powerful tool to extract the core information hidden in high-dimensional data in the past decades. However, as most of the sufficient dimension reduction methods provide linear combinations of the original predictors, interpreting the extracted components becomes challenging. Sparse sufficient dimension reduction was introduced in a past study to facilitate simpler interpretation by producing sparse estimates. Sparse directional regression is introduced by extending the proposed methods of another study. To demonstrate the competitiveness of the method, the performance of sparse directional regression is compared with that of sparse sliced inverse regression and sliced average variance estimation through numerical experiments. The method is further applied to the large-scale wave energy farm dataset.
