|
Activity Number:
|
406
- New Methodologies and Modern Data Applications
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #306816
|
Presentation
|
|
Title:
|
Bi-Clustering of Multivariate Regression Models:
|
|
Author(s):
|
Raja Velu* and Zhaoque Zhou
|
|
Companies:
|
Syracuse University and Syracuse University
|
|
Keywords:
|
Big data;
Multivariate regression
|
|
Abstract:
|
The clustering of regression models is of interest in many areas of research where the relationship between two sets of variables is similar across units. In this paper, we study the clustering of multivariate regression models where the predictors differ for the response variables. We extend the methodology for the model where the predictors are the same to this more realistic setting. We also consider sparseness issues and suggest some possible computational algorithms. The methods are illustrated with an example from finance where the focus is on relating the commonality in returns and the commonality in order flows for Dow Jones 30-stocks. Substantive implications will be discussed.
|
Authors who are presenting talks have a * after their name.
