A Scalable Framework for Minimum Distance Estimation with Applications to Mixture Modeling and Robust, Structured Regression

• Activity Number: 32
• Type: Contributed
• Date/Time: Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Computing
• Author(s): Jocelyn Chi* and Eric Chi
• Companies: North Carolina State University and North Carolina State University
• Keywords: robust ; minimum distance ; mixture models ; penalization ; sparsity ; majorization-minimization

Abstract

In this paper, we present a computational algorithm for performing mixture modeling and robust, structured regression using the L2E method, a minimum distance estimator. Previous implementations for the method were limited to fitting only a handful of parameters. We introduce an iterative majorization framework for extending the L2E method proposed in Scott (2001, 2009) to handling high-dimensional models. We demonstrate our algorithm on simulated and real data examples.