Online Program Home
My Program

Abstract Details

Activity Number: 152 - Frontiers of High-Dimensional and Complex Data analysis
Type: Topic Contributed
Date/Time: Monday, July 30, 2018 : 10:30 AM to 12:20 PM
Sponsor: International Chinese Statistical Association
Abstract #328935 Presentation
Title: A Bernstein-Type Inequality for U-Statistics Under Mixing Conditions
Author(s): Fang Han* and Yandi Shen and Daniela Witten
Companies: University of Washington and University of Washington and University of Washington
Keywords: U-statistics; Cramer-type moderate deviation; mixing condition; stochastic regression; stationarity test

This talk shows a Bernstein-type inequality along with a Cramer-type moderate deviation theorem for non-degenerate U-statistics under alpha- and tau-mixing conditions. The result confirms a conjecture raised by Borisov and Volodko (2015), and is applicable to a wide range of kernel functions via multiple Fourier series expansion. Two statistical applications of our theory are provided, covering estimation and testing problems in high dimensions.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program