Visualization tool of variable selection in bias-variance tradeoff for inverse probability weights.
Bias-variance tradeoff
High-dimensional covariates
Inverse probability weighting
Visualization
Journal
Annals of epidemiology
ISSN: 1873-2585
Titre abrégé: Ann Epidemiol
Pays: United States
ID NLM: 9100013
Informations de publication
Date de publication:
01 2020
01 2020
Historique:
received:
25
04
2019
revised:
27
11
2019
accepted:
10
12
2019
pubmed:
27
1
2020
medline:
2
6
2020
entrez:
27
1
2020
Statut:
ppublish
Résumé
Inversed probability weighted (IPW) estimators are commonly used to adjust for time-fixed or time-varying confounders. However, in high-dimensional settings, including all identified confounders may result in unstable weights leading to higher variance. We aimed to develop a visualization tool demonstrating the impact of each confounder on the bias and variance of IPW estimates, as well as the propensity score overlap. A SAS macro was developed for this visualization tool and we demonstrate how this tool can be used to identify potentially problematic confounders of the association of statin use after myocardial infarction on one-year mortality in a plasmode simulation study using a cohort of 39,792 patients from the UK (1998-2012). Through the tool's output, we can identify problematic confounders (two instrumental variables) and important confounders by comparing the estimated psuedo MSE with that from the fully adjusted model and propensity score overlap plot. Our results suggest that the analytic impact of all confounders should be considered carefully when fitting IPW estimators.
Identifiants
pubmed: 31982245
pii: S1047-2797(19)30277-7
doi: 10.1016/j.annepidem.2019.12.006
pmc: PMC7864095
mid: NIHMS1664801
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
56-59Subventions
Organisme : NICHD NIH HHS
ID : R01 HD072008
Pays : United States
Organisme : NICHD NIH HHS
ID : R21 HD065807
Pays : United States
Informations de copyright
Copyright © 2019. Published by Elsevier Inc.
Références
Stat Med. 2007 Jan 15;26(1):20-36
pubmed: 17072897
Comput Stat Data Anal. 2014 Apr;72:219-226
pubmed: 24587587
Am J Epidemiol. 2008 Sep 15;168(6):656-64
pubmed: 18682488
Annu Rev Public Health. 2015 Mar 18;36:89-108
pubmed: 25785886
Int J Biostat. 2010;6(1):Article 18
pubmed: 21731530
Stat Med. 2015 Dec 10;34(28):3661-79
pubmed: 26238958
Epidemiology. 2000 Sep;11(5):550-60
pubmed: 10955408
Am J Epidemiol. 2010 Mar 15;171(6):674-7; discussion 678-81
pubmed: 20139125
Int J Biostat. 2010 May 17;6(1):Article 17
pubmed: 20628637
Int J Epidemiol. 2016 Apr;45(2):565-75
pubmed: 27097747
BMJ. 2016 Apr 27;352:i1981
pubmed: 27121591
BMC Med Res Methodol. 2008 Oct 30;8:70
pubmed: 18973665
Int J Biostat. 2016 Nov 1;12(2):
pubmed: 27889705