Cargando…

Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables

The main concept behind causality involves both statistical conditions and temporal relations. However, current approaches to causal inference, focusing on the probability vs. conditional probability contrast, are based on model functions or parametric estimation. These approaches are not appropriat...

Descripción completa

Detalles Bibliográficos
Autores principales: Yin, Yu, Yao, Dezhong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4937367/
https://www.ncbi.nlm.nih.gov/pubmed/27389921
http://dx.doi.org/10.1038/srep29192
_version_ 1782441699369287680
author Yin, Yu
Yao, Dezhong
author_facet Yin, Yu
Yao, Dezhong
author_sort Yin, Yu
collection PubMed
description The main concept behind causality involves both statistical conditions and temporal relations. However, current approaches to causal inference, focusing on the probability vs. conditional probability contrast, are based on model functions or parametric estimation. These approaches are not appropriate when addressing non-stationary variables. In this work, we propose a causal inference approach based on the analysis of Events of Relations (CER). CER focuses on the temporal delay relation between cause and effect, and a binomial test is established to determine whether an “event of relation” with a non-zero delay is significantly different from one with zero delay. Because CER avoids parameter estimation of non-stationary variables per se, the method can be applied to both stationary and non-stationary signals.
format Online
Article
Text
id pubmed-4937367
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Nature Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-49373672016-07-13 Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables Yin, Yu Yao, Dezhong Sci Rep Article The main concept behind causality involves both statistical conditions and temporal relations. However, current approaches to causal inference, focusing on the probability vs. conditional probability contrast, are based on model functions or parametric estimation. These approaches are not appropriate when addressing non-stationary variables. In this work, we propose a causal inference approach based on the analysis of Events of Relations (CER). CER focuses on the temporal delay relation between cause and effect, and a binomial test is established to determine whether an “event of relation” with a non-zero delay is significantly different from one with zero delay. Because CER avoids parameter estimation of non-stationary variables per se, the method can be applied to both stationary and non-stationary signals. Nature Publishing Group 2016-07-08 /pmc/articles/PMC4937367/ /pubmed/27389921 http://dx.doi.org/10.1038/srep29192 Text en Copyright © 2016, Macmillan Publishers Limited http://creativecommons.org/licenses/by/4.0/ This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
spellingShingle Article
Yin, Yu
Yao, Dezhong
Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title_full Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title_fullStr Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title_full_unstemmed Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title_short Causal Inference Based on the Analysis of Events of Relations for Non-stationary Variables
title_sort causal inference based on the analysis of events of relations for non-stationary variables
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4937367/
https://www.ncbi.nlm.nih.gov/pubmed/27389921
http://dx.doi.org/10.1038/srep29192
work_keys_str_mv AT yinyu causalinferencebasedontheanalysisofeventsofrelationsfornonstationaryvariables
AT yaodezhong causalinferencebasedontheanalysisofeventsofrelationsfornonstationaryvariables