Online Program Home
My Program

Abstract Details

Activity Number: 243 - Functional Object Analysis and Beyond
Type: Contributed
Date/Time: Monday, July 29, 2019 : 2:00 PM to 3:50 PM
Sponsor: IMS
Abstract #307307
Title: Edgeworth Expansions for Minimum Divergence Estimators
Author(s): Zhengyang Fan* and Anand Vidyashankar
Companies: and George Mason University
Keywords: differentially private; robust; efficient; divergence ; Edgeworth expansion; healthcare

Minimum divergence estimators possess the dual property of efficiency and robustness and are being increasingly used in a various scientific investigations. In privacy applications, it is of interest to obtain estimators that are efficient and differentially private. However, the resulting estimators are highly non-robust leading to incorrect inferences. In this presentation, we describe new higher order Edgeworth expansions for minimum divergence estimators and use them to obtain robust, efficient and differentially private estimators. We demonstrate our results using simulating and using real data in healthcare settings. Implications of our results to policy development will also be provided.

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

Back to the full JSM 2019 program