|
Activity Number:
|
102
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 1, 2016 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #318428
|
View Presentation
|
|
Title:
|
Nonparametric Regression with Instrumental Variables
|
|
Author(s):
|
Purushottam Laud* and Robert McCulloch and Rodney Sparapani
|
|
Companies:
|
Medical College of Wisconsin and The University of Chicago and Medical College of Wisconsin
|
|
Keywords:
|
endogeneity ;
non-linearity ;
Gibbs conditionals
|
|
Abstract:
|
Regression models with instrumental variables are used widely in econometrics and in biomedical applications. Typically, a linear or additive model formulation is used with joint nonparametric errors. We employ Bayesian additive regression trees and a limited additivity assumption to allow much more flexible relationships that include interactions and non-linearities. After a full model description we address how Gibbs conditionals can be obtained for sampling the posterior. We illustrate the method with some well-known examples in the literature.
|
Authors who are presenting talks have a * after their name.
