Printable PDF
Department of Mathematics,
Department of Mathematics,
University of California San Diego
****************************
Advancement to Candidacy
Xiaoou Pan
UCSD
On Quantile Regression: Non-Asymptotic Theory, Smoothing and Multiplier Bootstrap
Abstract:
We establish non-asymptotic concentration bound and Bahadur representation for quantile regression estimator in the random design setting. Smoothed quantile regression is then proposed with fast computation and high estimation accuracy. Finally, we provide rigorous theoretical guarantees for the validity of inference via multiplier bootstrap.
Advisor: Wenxin Zhou
November 8, 2019
11:30 AM
AP&M 6402
****************************
