Methods for dealing with time‐dependent confounding

R.M. Daniel; S. N. Cousens; B. L. De Stavola; M. G. Kenward; J. A. C. Sterne

doi:10.1002/sim.5686

journal article Dec 03, 2012

Methods for dealing with time‐dependent confounding

R.M. Daniel S. N. Cousens B. L. De Stavola M. G. Kenward J. A. C. Sterne

Statistics in Medicine Vol. 32 No. 9 pp. 1584-1618 · Wiley

View at Publisher Save 10.1002/sim.5686

Abstract

Longitudinal studies, where data are repeatedly collected on subjects over a period, are common in medical research. When estimating the effect of a time‐varying treatment or exposure on an outcome of interest measured at a later time, standard methods fail to give consistent estimators in the presence of time‐varying confounders if those confounders are themselves affected by the treatment. Robins and colleagues have proposed several alternative methods that, provided certain assumptions hold, avoid the problems associated with standard approaches. They include the g‐computation formula, inverse probability weighted estimation of marginal structural models and g‐estimation of structural nested models. In this tutorial, we give a description of each of these methods, exploring the links and differences between them and the reasons for choosing one over the others in different settings. Copyright © 2012 John Wiley & Sons, Ltd.

Topics

No keywords indexed for this article. Browse by subject →

References

47

[1]

10.1016/0270-0255(86)90088-6

[2]

Marginal Structural Models and Causal Inference in Epidemiology

James M. Robins, Miguel Ángel Hernán, Babette Brumback

Epidemiology 10.1097/00001648-200009000-00011

[3]

10.1097/00001648-199207000-00007

[4]

Robins JM (2009)

[5]

10.1093/biomet/79.2.321

[6]

10.1093/oxfordjournals.aje.a009658

[7]

10.1093/aje/155.8.710

[8]

10.1097/00001648-200009000-00012

[9]

10.1214/aos/1176344064

[10]

10.1097/ede.0b013e3181bd5638

[11]

10.1177/0962280210391076

[12]

10.1097/00001648-199901000-00008

[13]

10.1023/a:1020315127304

[14]

10.1097/01.ede.0000135174.63482.43

[15]

Robins JM (1997)

[16]

10.1016/j.ejim.2006.11.009

[17]

Gformula: Estimating Causal Effects in the Presence of Time-Varying Confounding or Mediation using the G-Computation Formula

Rhian M. Daniel, B. L. De Stavola, S. N. Cousens

The Stata Journal: Promoting communications on sta... 10.1177/1536867x1201100401

[18]

10.1016/j.csda.2006.06.013

[19]

10.1093/ije/dyp192

[20]

10.1093/biomet/63.3.581

[21]

Constructing Inverse Probability Weights for Marginal Structural Models

S. R. Cole, M. A. Hernan

American Journal of Epidemiology 10.1093/aje/kwn164

[22]

10.1177/1536867x0400400403

[23]

Implementation of G-Computation on a Simulated Data Set: Demonstration of a Causal Inference Technique

Jonathan M. Snowden, Sherri Rose, Kathleen M. Mortimer

American Journal of Epidemiology 10.1093/aje/kwq472

[24]

10.1214/ss/1009211805

[25]

Simpson EH "The interpretation of interaction in contingency tables" Journal of the Royal Statistical Society Series B (1951) 10.1111/j.2517-6161.1951.tb00088.x

[26]

10.1214/07-sts227

[27]

10.1214/07-sts227a

[28]

Robins JM (1993)

[29]

10.1080/03610929408831393

[30]

Casella G (2002)

[31]

10.1177/1536867x0200200205

[32]

Tsiatis AA (2006)

[33]

Doubly Robust Estimation in Missing Data and Causal Inference Models

Heejung Bang, James M. Robins

Biometrics 10.1111/j.1541-0420.2005.00377.x

[34]

10.1111/j.1467-9868.2008.00673.x

[35]

10.2202/1557-4679.1109

[36]

10.1093/biomet/asq035

[37]

10.1093/biomet/asp033

[38]

10.1177/0962280210387717

[39]

10.1002/sim.3301

[40]

10.1007/978-1-4419-9076-1_11

[41]

10.1111/j.1742-7843.2006.pto_329.x

[42]

Orellana L "Dynamic regime marginal structural mean models for estimation of optimal dynamic treatment regimes, Part I: main content" The International Journal of Biostatistics (2010)

[43]

10.2202/1557-4679.1212

[44]

10.1093/biomet/asm097

[45]

10.1093/aje/kwq474

[46]

10.1093/biomet/asq053

[47]

10.1080/01621459.2012.682532

Cited By

301

So Many Choices: A Guide to Selecting Among Methods to Adjust for Observed Confounders

Luke Keele, Richard Grieve · 2025

Statistics in Medicine

Causal Inference and Estimands in Clinical Trials

Ilya Lipkovich, Bohdana Ratitch · 2020

Statistics in Biopharmaceutical Res...

Sources of confounding in life course epidemiology

S. Santos, D. Zugna · 2018

Journal of Developmental Origins of...

STRengthening Analytical Thinking for Observational Studies: the STRATOS initiative

Willi Sauerbrei, Michal Abrahamowicz · 2014

Statistics in Medicine

Metrics

301

Citations

47

References

Details

Published: Dec 03, 2012
Vol/Issue: 32(9)
Pages: 1584-1618
License: View

Authors

R

R.M. Daniel

Centre for Statistical Methodology London School of Hygiene and Tropical Medicine London U.K.

S

S. N. Cousens

Centre for Statistical Methodology London School of Hygiene and Tropical Medicine London U.K.

B

B. L. De Stavola

Centre for Statistical Methodology London School of Hygiene and Tropical Medicine London U.K.

M

M. G. Kenward

Centre for Statistical Methodology London School of Hygiene and Tropical Medicine London U.K.

J

J. A. C. Sterne

Department of Social Medicine University of Bristol Bristol U.K.

Cite This Article

R.M. Daniel, S. N. Cousens, B. L. De Stavola, et al. (2012). Methods for dealing with time‐dependent confounding. Statistics in Medicine, 32(9), 1584-1618. https://doi.org/10.1002/sim.5686

Methods for dealing with time‐dependent confounding

You May Also Like