Online Program Home
My Program

Abstract Details

Activity Number: 528 - Analysis of Big Data
Type: Contributed
Date/Time: Wednesday, August 1, 2018 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #330251 Presentation
Title: Penalized Jackknife Empirical Likelihood in High Dimension
Author(s): Na Zhao* and jinfeng Xu
Companies: and The University of Hong Kong
Keywords: Estimationg equation; High-dimensional data analysis; Jackknife empirical likelihood ; Penalized likelihood ; U-statistics; Variable selection
Abstract:

Jackknife empirical likelihood(JEL) proposed by Jing, Yuan and Zhou(2009)is an attractive approach for statistical inferences with nonlinear statistics such as U-statistics. However, most contemporary problem involving high dimension model selection and the number of parameters diverges to infinity. We propose a penalized JEL method which preserves the main advantages of JEL and leads to reliable variable selection based on the estimating equations with U-statistic structure in the high-dimensional framework. Under certain regularity conditions, we establish the asymptotic theory and oracle property for the JEL and its penalized version when the number of estimating equations and parameters may increase as the sample size increases. Simulation studies were carried out to examine the performance of the proposed methods, we also apply our method to real data sets and obtain encouraging results.


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

Back to the full JSM 2018 program