TY - JOUR
T1 - Combining Effect Estimates Across Cohorts and Sufficient Adjustment Sets for Collaborative Research
T2 - A Simulation Study
AU - on behalf of program collaborators for Environmental influences on Child Health Outcomes
AU - Hamra, Ghassan B.
AU - Lesko, Catherine R.
AU - Buckley, Jessie P.
AU - Jensen, Elizabeth T.
AU - Tancredi, Daniel
AU - Lau, Bryan
AU - Hertz-Picciotto, Irva
N1 - Publisher Copyright:
© 2021 Lippincott Williams and Wilkins. All rights reserved.
PY - 2021/5/1
Y1 - 2021/5/1
N2 - Background: Collaborative research often combines findings across multiple, independent studies via meta-analysis. Ideally, all study estimates that contribute to the meta-analysis will be equally unbiased. Many meta-analyses require all studies to measure the same covariates. We explored whether differing minimally sufficient sets of confounders identified by a directed acyclic graph (DAG) ensures comparability of individual study estimates. Our analysis applied four statistical estimators to multiple minimally sufficient adjustment sets identified in a single DAG. Methods: We compared estimates obtained via linear, log-binomial, and logistic regression and inverse probability weighting, and data were simulated based on a previously published DAG. Results: Our results show that linear, log-binomial, and inverse probability weighting estimators generally provide the same estimate of effect for different estimands that are equally sufficient to adjust confounding bias, with modest differences in random error. In contrast, logistic regression often performed poorly, with notable differences in effect estimates obtained from unique minimally sufficient adjustment sets, and larger standard errors than other estimators. Conclusions: Our findings do not support the reliance of collaborative research on logistic regression results for meta-analyses. Use of DAGs to identify potentially differing minimally sufficient adjustment sets can allow meta-analyses without requiring the exact same covariates.
AB - Background: Collaborative research often combines findings across multiple, independent studies via meta-analysis. Ideally, all study estimates that contribute to the meta-analysis will be equally unbiased. Many meta-analyses require all studies to measure the same covariates. We explored whether differing minimally sufficient sets of confounders identified by a directed acyclic graph (DAG) ensures comparability of individual study estimates. Our analysis applied four statistical estimators to multiple minimally sufficient adjustment sets identified in a single DAG. Methods: We compared estimates obtained via linear, log-binomial, and logistic regression and inverse probability weighting, and data were simulated based on a previously published DAG. Results: Our results show that linear, log-binomial, and inverse probability weighting estimators generally provide the same estimate of effect for different estimands that are equally sufficient to adjust confounding bias, with modest differences in random error. In contrast, logistic regression often performed poorly, with notable differences in effect estimates obtained from unique minimally sufficient adjustment sets, and larger standard errors than other estimators. Conclusions: Our findings do not support the reliance of collaborative research on logistic regression results for meta-analyses. Use of DAGs to identify potentially differing minimally sufficient adjustment sets can allow meta-analyses without requiring the exact same covariates.
KW - Collaborative research
KW - Directed acyclic graph
KW - Simulation
UR - http://www.scopus.com/inward/record.url?scp=85103682488&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85103682488&partnerID=8YFLogxK
U2 - 10.1097/EDE.0000000000001336
DO - 10.1097/EDE.0000000000001336
M3 - Article
C2 - 33591054
AN - SCOPUS:85103682488
SN - 1044-3983
VL - 32
SP - 421
EP - 424
JO - Epidemiology
JF - Epidemiology
IS - 3
ER -