Model Averaging for Improving Inference from Causal Diagrams

Model selection is an integral, yet contentious, component of epidemiologic research. Unfortunately, there remains no consensus on how to identify a single, best model among multiple candidate models. Researchers may be prone to selecting the model that best supports their a priori, preferred result...

Full description

Bibliographic Details
Main Authors:	Hamra, Ghassan B., Kaufman, Jay S., Vahratian, Anjel
Format:	Online
Language:	English
Published:	MDPI 2015
Online Access:	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4555287/

id	pubmed-4555287
recordtype	oai_dc
spelling	pubmed-45552872015-09-01 Model Averaging for Improving Inference from Causal Diagrams Hamra, Ghassan B. Kaufman, Jay S. Vahratian, Anjel Article Model selection is an integral, yet contentious, component of epidemiologic research. Unfortunately, there remains no consensus on how to identify a single, best model among multiple candidate models. Researchers may be prone to selecting the model that best supports their a priori, preferred result; a phenomenon referred to as “wish bias”. Directed acyclic graphs (DAGs), based on background causal and substantive knowledge, are a useful tool for specifying a subset of adjustment variables to obtain a causal effect estimate. In many cases, however, a DAG will support multiple, sufficient or minimally-sufficient adjustment sets. Even though all of these may theoretically produce unbiased effect estimates they may, in practice, yield somewhat distinct values, and the need to select between these models once again makes the research enterprise vulnerable to wish bias. In this work, we suggest combining adjustment sets with model averaging techniques to obtain causal estimates based on multiple, theoretically-unbiased models. We use three techniques for averaging the results among multiple candidate models: information criteria weighting, inverse variance weighting, and bootstrapping. We illustrate these approaches with an example from the Pregnancy, Infection, and Nutrition (PIN) study. We show that each averaging technique returns similar, model averaged causal estimates. An a priori strategy of model averaging provides a means of integrating uncertainty in selection among candidate, causal models, while also avoiding the temptation to report the most attractive estimate from a suite of equally valid alternatives. MDPI 2015-08-11 2015-08 /pmc/articles/PMC4555287/ /pubmed/26270672 http://dx.doi.org/10.3390/ijerph120809391 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
repository_type	Open Access Journal
institution_category	Foreign Institution
institution	US National Center for Biotechnology Information
building	NCBI PubMed
collection	Online Access
language	English
format	Online
author	Hamra, Ghassan B. Kaufman, Jay S. Vahratian, Anjel
spellingShingle	Hamra, Ghassan B. Kaufman, Jay S. Vahratian, Anjel Model Averaging for Improving Inference from Causal Diagrams
author_facet	Hamra, Ghassan B. Kaufman, Jay S. Vahratian, Anjel
author_sort	Hamra, Ghassan B.
title	Model Averaging for Improving Inference from Causal Diagrams
title_short	Model Averaging for Improving Inference from Causal Diagrams
title_full	Model Averaging for Improving Inference from Causal Diagrams
title_fullStr	Model Averaging for Improving Inference from Causal Diagrams
title_full_unstemmed	Model Averaging for Improving Inference from Causal Diagrams
title_sort	model averaging for improving inference from causal diagrams
description	Model selection is an integral, yet contentious, component of epidemiologic research. Unfortunately, there remains no consensus on how to identify a single, best model among multiple candidate models. Researchers may be prone to selecting the model that best supports their a priori, preferred result; a phenomenon referred to as “wish bias”. Directed acyclic graphs (DAGs), based on background causal and substantive knowledge, are a useful tool for specifying a subset of adjustment variables to obtain a causal effect estimate. In many cases, however, a DAG will support multiple, sufficient or minimally-sufficient adjustment sets. Even though all of these may theoretically produce unbiased effect estimates they may, in practice, yield somewhat distinct values, and the need to select between these models once again makes the research enterprise vulnerable to wish bias. In this work, we suggest combining adjustment sets with model averaging techniques to obtain causal estimates based on multiple, theoretically-unbiased models. We use three techniques for averaging the results among multiple candidate models: information criteria weighting, inverse variance weighting, and bootstrapping. We illustrate these approaches with an example from the Pregnancy, Infection, and Nutrition (PIN) study. We show that each averaging technique returns similar, model averaged causal estimates. An a priori strategy of model averaging provides a means of integrating uncertainty in selection among candidate, causal models, while also avoiding the temptation to report the most attractive estimate from a suite of equally valid alternatives.
publisher	MDPI
publishDate	2015
url	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4555287/
_version_	1613471127579918336

Model Averaging for Improving Inference from Causal Diagrams

Similar Items