Online Program Home
My Program

Abstract Details

Activity Number: 76 - To Open Source, or Not
Type: Contributed
Date/Time: Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
Sponsor: Section for Statistical Programmers and Analysts
Abstract #305077
Title: Doubly Distributed and Integrated Inference for Correlated Data with Heterogeneous Parameters
Author(s): Emily Charlotte Hector* and Peter X.K. Song
Companies: University of Michigan and School of Public Health, University of Michigan
Keywords: Divide-and-conquer; Generalized method of moments; Parallel computing; Scalable computing

We present a divide-and-conquer procedure implemented in a distributed and parallelized MapReduce scheme for statistical estimation and inference of regression parameters with high-dimensional correlated responses with multi-level nested correlations. The proposed method overcomes the computational cost associated with existing statistical methods by dividing subjects into independent groups and responses into subvectors to be analyzed separately and in parallel on a distributed platform. A broad class of models is available in this framework, and we allow for heterogeneity of the parameter of interest for a more flexible model fit. Theoretical challenges related to combining results from dependent data are overcome in a statistically efficient way using a meta-estimator derived from Hansen’s Generalized Method of Moments. We provide a rigorous theoretical framework for efficient estimation, inference, and goodness-of-fit tests. We develop an R package for ease of implementation.

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

Back to the full JSM 2019 program