Online Program Home
My Program

Abstract Details

Activity Number: 73
Type: Contributed
Date/Time: Sunday, July 31, 2016 : 4:00 PM to 5:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #320661 View Presentation
Title: Efficient Robust Regression with Variable Selection via Generalized Empirical Likelihood
Author(s): Sohini Raha* and Howard Bondell
Companies: North Carolina State University and North Carolina State University
Keywords: variable selection ; outliers ; generalized empirical likelihood

In statistics, presence of outliers in a data with large number of predictors is often very difficult to work with. Although there are numerous procedures to eliminate the effect of outliers effectively, and variable selection separately, there is no effective way to deal with both of them simultaneously. So here, we are proposing a method of robust regression with variable selection via two-stage generalized empirical likelihood. Efficiency comes from the estimator's close connection with generalized empirical likelihood and in variable selection we use the concept of penalty as in lasso, so it also tends to produce some coefficients that are exactly equal to 0 and hence give interpret-able models.

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

Back to the full JSM 2016 program

Copyright © American Statistical Association