Activity Number:
|
189
- Nonparametric Methods in Big or Complex Data
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract #311079
|
|
Title:
|
Concurrent Object Regression (CORE) with Euclidean Predictors
|
Author(s):
|
Satarupa Bhattacharjee* and Hans-Georg Müller
|
Companies:
|
University of California and University of California, Davis
|
Keywords:
|
Concurrent regression;
general metric space objects;
Fréchet regression;
functional Magnetic Resonance Imaging
|
Abstract:
|
Modern-day problems in statistics often face the challenge of exploring and analyzing complex non-Euclidean object data that do not conform to vector space structures or operations. Examples of such data objects include covariance matrices, graph Laplacians of networks and univariate probability distribution functions. We propose a new concurrent regression model to characterize the time-varying relation between an object in general metric space (as a response) and a real-valued vector (as a predictor), where we make use of concepts from Fréchet regression. We develop generalized versions of both global linear regression and local weighted least squares type concurrent regression for responses which are situated in general metric spaces and propose estimators that can accommodate sparse and/or irregular designs. We illustrate the proposed models relating mortality data for various countries to their time-varying GDP and resting-state functional Magnetic Resonance Imaging data (fMRI) to a neuro-cognitive score.
|
Authors who are presenting talks have a * after their name.