CoChat
Sign Up
Cited by 548Advanced Causal Inference TechniquesStatistical Methods in EpidemiologyBayesian Modeling and Causal Inference

Fallibility in estimating direct effects

Cole, Stephen R, Hernán, Miguel A·2002·International Journal of Epidemiology
DOI 10.1093/ije/31.1.163
Open this paper in CoChat — free account

Abstract

We use causal graphs and a partly hypothetical example from the Physicians' Health Study to explain why a common standard method for quantifying direct effects (i.e. stratifying on the intermediate variable) may be flawed. Estimating direct effects without bias requires that two assumptions hold, namely the absence of unmeasured confounding for (1) exposure and outcome, and (2) the intermediate variable and outcome. Recommendations include collecting and incorporating potential confounders for the causal effect of the mediator on the outcome, as well as the causal effect of the exposure on the outcome, and clearly stating the additional assumption that there is no unmeasured confounding for the causal effect of the mediator on the outcome.

Integrity signals

Registry

Crossref · 10.1093/ije/31.1.163

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • SCM weeds out myths and misconceptions from outdated traditions.

    “Weeding out myths and misconceptions from outdated traditions (Meek and Glymour, 1994; Greenland et al., 1999; Cole and Hern´ an, 2002; Arah, 2008; Shrier, 2009; Pearl, 2009b).”

    From Causal inference in statistics: An overview (2009) · cites this paper as Cole and Hern´ an, 2002

  • It will not be sufficient to measure the association between gender (X) and hiring (Y) for a given level of qualification Z, because conditioning on the mediator Z may create spurious associations between X and Y even when there is no direct effect of X on Y.

    “For example, it will not be sufficient to measure the association between gender ( X ) and hiring ( Y ) for a given level of qualification Z , because, by conditioning on the mediator Z , we may create spurious associations between X and Y even when there is no direct effect of X on Y (Pearl, 1998; Cole and Hern´ an, 2002).”

    From Causal inference in statistics: An overview (2009) · cites this paper as Cole and Hernán, 2002

  • SCM weeds out myths and misconceptions from outdated traditions.

    “Weeding out myths and misconceptions from outdated traditions (Meek and Glymour, 1994, Greenland et al., 1999, Cole and Hernan, 2002, Arah, 2008, Shrier, 2009, Pearl, 2009c).”

    From An Introduction to Causal Inference (2010) · cites this paper as Cole and Hernan, 2002

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Cole, S. R., & Hernán, M. A.
Affiliations
Johns Hopkins University (US)
Corresponding author
Cole, Stephen R
ORCID
Cole, Stephen R
Venue
International Journal of Epidemiology
Publisher
Oxford University Press (OUP)
Published
2002-02
Volume
31
Issue
1
Pages
163-165
ISSN
  • 0300-5771 (ISSN-L)
  • 1464-3685
DOI
10.1093/ije/31.1.163
OpenAlex
W2157524492
Cited by
548
References
5
Citations by year
2026: 8 · 2025: 11 · 2024: 12 · 2023: 13 · 2022: 21 · 2021: 12 · 2020: 12 · 2019: 23 · 2018: 4 · 2017: 24 · 2016: 25 · 2015: 34 · 2014: 48 · 2013: 26 · 2012: 46
FWCI
14.57
Type
journal article
Language
en
Open access
closed
Locations
  • International Journal of Epidemiology (publishedVersion)
  • PubMed (publishedVersion)
Funders
National Institute of Allergy and Infectious Diseases (U01 AI42590, U01AI042590, U01AI035043, U01 AI-35043)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
Keywords
direct effect, mediation analysis, unmeasured confounding, causal graphs, Physicians' Health Study, causal inference
MeSH terms
Aspirin, Humans, Myocardial Infarction, Platelet Aggregation Inhibitors, Epidemiologic Research Design, Bias, Causality, Confounding Factors, Epidemiologic, Odds Ratio

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review