Applied causal inference methods for sequential mediators.
Causal inference
Direct and indirect effects
Imputation
Mediation analysis
Sequential mediators
Weighting
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
24 11 2022
24 11 2022
Historique:
received:
22
04
2022
accepted:
19
10
2022
entrez:
24
11
2022
pubmed:
25
11
2022
medline:
29
11
2022
Statut:
epublish
Résumé
Mediation analysis aims at estimating to what extent the effect of an exposure on an outcome is explained by a set of mediators on the causal pathway between the exposure and the outcome. The total effect of the exposure on the outcome can be decomposed into an indirect effect, i.e. the effect explained by the mediators jointly, and a direct effect, i.e. the effect unexplained by the mediators. However finer decompositions are possible in presence of independent or sequential mediators. We review four statistical methods to analyse multiple sequential mediators, the inverse odds ratio weighting approach, the inverse probability weighting approach, the imputation approach and the extended imputation approach. These approaches are compared and implemented using a case-study with the aim to investigate the mediating role of adverse reproductive outcomes and infant respiratory infections in the effect of maternal pregnancy mental health on infant wheezing in the Ninfea birth cohort. Using the inverse odds ratio weighting approach, the direct effect of maternal depression or anxiety in pregnancy is equal to a 59% (95% CI: 27%,94%) increased prevalence of infant wheezing and the mediated effect through adverse reproductive outcomes is equal to a 3% (95% CI: -6%,12%) increased prevalence of infant wheezing. When including infant lower respiratory infections in the mediation pathway, the direct effect decreases to 57% (95% CI: 25%,92%) and the indirect effect increases to 5% (95% CI: -5%,15%). The estimates of the effects obtained using the weighting and the imputation approaches are similar. The extended imputation approach suggests that the small joint indirect effect through adverse reproductive outcomes and lower respiratory infections is due entirely to the contribution of infant lower respiratory infections, and not to an increased prevalence of adverse reproductive outcomes. The four methods revealed similar results of small mediating role of adverse reproductive outcomes and early respiratory tract infections in the effect of maternal pregnancy mental health on infant wheezing. The choice of the method depends on what is the effect of main interest, the type of the variables involved in the analysis (binary, categorical, count or continuous) and the confidence in specifying the models for the exposure, the mediators and the outcome.
Sections du résumé
BACKGROUND
Mediation analysis aims at estimating to what extent the effect of an exposure on an outcome is explained by a set of mediators on the causal pathway between the exposure and the outcome. The total effect of the exposure on the outcome can be decomposed into an indirect effect, i.e. the effect explained by the mediators jointly, and a direct effect, i.e. the effect unexplained by the mediators. However finer decompositions are possible in presence of independent or sequential mediators.
METHODS
We review four statistical methods to analyse multiple sequential mediators, the inverse odds ratio weighting approach, the inverse probability weighting approach, the imputation approach and the extended imputation approach. These approaches are compared and implemented using a case-study with the aim to investigate the mediating role of adverse reproductive outcomes and infant respiratory infections in the effect of maternal pregnancy mental health on infant wheezing in the Ninfea birth cohort.
RESULTS
Using the inverse odds ratio weighting approach, the direct effect of maternal depression or anxiety in pregnancy is equal to a 59% (95% CI: 27%,94%) increased prevalence of infant wheezing and the mediated effect through adverse reproductive outcomes is equal to a 3% (95% CI: -6%,12%) increased prevalence of infant wheezing. When including infant lower respiratory infections in the mediation pathway, the direct effect decreases to 57% (95% CI: 25%,92%) and the indirect effect increases to 5% (95% CI: -5%,15%). The estimates of the effects obtained using the weighting and the imputation approaches are similar. The extended imputation approach suggests that the small joint indirect effect through adverse reproductive outcomes and lower respiratory infections is due entirely to the contribution of infant lower respiratory infections, and not to an increased prevalence of adverse reproductive outcomes.
CONCLUSIONS
The four methods revealed similar results of small mediating role of adverse reproductive outcomes and early respiratory tract infections in the effect of maternal pregnancy mental health on infant wheezing. The choice of the method depends on what is the effect of main interest, the type of the variables involved in the analysis (binary, categorical, count or continuous) and the confidence in specifying the models for the exposure, the mediators and the outcome.
Identifiants
pubmed: 36424556
doi: 10.1186/s12874-022-01764-w
pii: 10.1186/s12874-022-01764-w
pmc: PMC9686042
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
301Informations de copyright
© 2022. The Author(s).
Références
Biometrics. 2015 Mar;71(1):1-14
pubmed: 25351114
Am J Epidemiol. 2012 Aug 1;176(3):190-5
pubmed: 22781427
Psychol Methods. 2013 Jun;18(2):137-50
pubmed: 23379553
Ann Stat. 2012 Jun;40(3):1816-1845
pubmed: 26770002
Eur J Epidemiol. 2007;22(12):831-7
pubmed: 17955333
Prev Sci. 2012 Aug;13(4):426-36
pubmed: 22419385
Epidemiol Biostat Public Health. 2014;11(2):
pubmed: 25580387
Epidemiology. 1992 Mar;3(2):143-55
pubmed: 1576220
Epidemiology. 2006 May;17(3):276-84
pubmed: 16617276
J Allergy Clin Immunol. 2009 Apr;123(4):847-53.e11
pubmed: 19348924
Int J Epidemiol. 2018 Feb 1;47(1):166-174
pubmed: 29040553
Am J Epidemiol. 2015 Mar 1;181(5):349-56
pubmed: 25693776
Psychol Methods. 2010 Dec;15(4):309-34
pubmed: 20954780
Epidemiol Methods. 2014 Jan;2(1):95-115
pubmed: 25580377
Epidemiology. 2017 Mar;28(2):258-265
pubmed: 27922534
Epidemiology. 2022 Nov 1;33(6):854-863
pubmed: 35816125
Int J Epidemiol. 2013 Oct;42(5):1511-9
pubmed: 24019424
Am J Epidemiol. 2010 Dec 15;172(12):1339-48
pubmed: 21036955
Allergol Immunopathol (Madr). 2018 May - Jun;46(3):210-217
pubmed: 27865539
Epidemiology. 2022 Nov 1;33(6):864-867
pubmed: 35816123
J Causal Inference. 2022 Jan;10(1):18-44
pubmed: 35633840
Epidemiology. 2014 Mar;25(2):300-6
pubmed: 24487213
Stat Methods Med Res. 2019 Jun;28(6):1793-1807
pubmed: 29869589
Am J Epidemiol. 2018 Jun 1;187(6):1311-1318
pubmed: 29140421
Epidemiology. 2021 Mar 1;32(2):209-219
pubmed: 33512846
Stat Med. 2013 Nov 20;32(26):4567-80
pubmed: 23744517
Am J Epidemiol. 2017 Jul 15;186(2):184-193
pubmed: 28472328
Eur Respir J. 2016 Jan;47(1):133-46
pubmed: 26541526