1
IRUS Total
Downloads
  Altmetric

A Bayesian nonparametric test for conditional independence

File Description SizeFormat 
FoDS_FINAL.pdfAccepted version688.96 kBAdobe PDFView/Open
Title: A Bayesian nonparametric test for conditional independence
Authors: Teymur, O
Filippi, S
Item Type: Journal Article
Abstract: This article introduces a Bayesian nonparametric method for quantifying the relative evidence in a dataset in favour of the dependence or independence of two variables conditional on a third. The approach uses Pólya tree priors on spaces of conditional probability densities, accounting for uncertainty in the form of the underlying distributions in a nonparametric way. The Bayesian perspective provides an inherently symmetric probability measure of conditional dependence or independence, a feature particularly advantageous in causal discovery and not employed in existing procedures of this type.
Issue Date: 1-Jun-2020
Date of Acceptance: 1-Jun-2020
URI: http://hdl.handle.net/10044/1/81568
DOI: 10.3934/fods.2020009
ISSN: 2639-8001
Publisher: American Institute of Mathematical Sciences
Start Page: 155
End Page: 172
Journal / Book Title: Foundations of Data Science
Volume: 2
Issue: 2
Copyright Statement: ©American Institute of Mathematical Sciences 2020. This is a pre-copy-editing, author-produced PDF of an article accepted for publication in Foundations of Data Sciencefollowing peer review. The definitive publisher-authenticated version is available online at:http://www.aimsciences.org/article/doi/10.3934/fods.2020009
Keywords: stat.ME
stat.ME
stat.CO
stat.ML
stat.ME
stat.ME
stat.CO
stat.ML
Publication Status: Published
Online Publication Date: 2020-07-28
Appears in Collections:Mathematics
Statistics