Online Program Home
  My Program

Abstract Details

Activity Number: 73 - Nonparametric Statistics in High-Dimensional Settings
Type: Contributed
Date/Time: Sunday, July 30, 2017 : 4:00 PM to 5:50 PM
Sponsor: Section on Nonparametric Statistics
Abstract #322847 View Presentation
Title: Additive Partially Linear Models for Massive Heterogeneous Data
Author(s): Binhuan Wang and Yixin Fang* and Heng Lian and Hua Liang
Companies: New York University School of Medicine and New Jersey Institute of Technology and City University of Hong Kong and George Washington University
Keywords: divide-and-conquer ; heterogeneity ; oracle property ; regression splines

We consider an additive partially linear framework for modelling massive heterogeneous data. The major goal is to extract multiple common features simultaneously across all sub-populations while exploring heterogeneity of each sub-population. This work generalizes the partially linear framework proposed in Zhao, Cheng and Liu (2016), which considers only one common feature. We propose an aggregation type of estimators for the commonality parameters that possess the asymptotic optimal bounds and the asymptotic distributions as if there were no heterogeneity. This oracle result holds when the number of sub-populations does not grow too fast and the tuning parameters are selected carefully. A plug-in estimator for the heterogeneity parameter is further constructed, and shown to possess the asymptotic distribution as if the commonality information were available. The performance of the proposed methods is evaluated via simulation studies and an application to the Medicare Provider Utilization and Payment data.

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

Back to the full JSM 2017 program

Copyright © American Statistical Association