CoChat
Sign Up
Cited by 90Advanced Causal Inference TechniquesStatistical Methods in EpidemiologyMeta-analysis and systematic reviews

Selection Bias When Estimating Average Treatment Effects Using One-sample Instrumental Variable Analysis

Open access
Hughes, Rachael A., Davies, Neil M., Davey Smith, George, Tilling, Kate·2019·Epidemiology
DOI 10.1097/ede.0000000000000972PMC PMC6525095

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Participants in epidemiologic and genetic studies are rarely true random samples of the populations they are intended to represent, and both known and unknown factors can influence participation in a study (known as selection into a study). The circumstances in which selection causes bias in an instrumental variable (IV) analysis are not widely understood by practitioners of IV analyses. We use directed acyclic graphs (DAGs) to depict assumptions about the selection mechanism (factors affecting selection) and show how DAGs can be used to determine when a two-stage least squares IV analysis is biased by different selection mechanisms. Through simulations, we show that selection can result in a biased IV estimate with substantial confidence interval (CI) undercoverage, and the level of bias can differ between instrument strengths, a linear and nonlinear exposure–instrument association, and a causal and noncausal exposure effect. We present an application from the UK Biobank study, which is known to be a selected sample of the general population. Of interest was the causal effect of staying in school at least 1 extra year on the decision to smoke. Based on 22,138 participants, the two-stage least squares exposure estimates were very different between the IV analysis ignoring selection and the IV analysis which adjusted for selection (e.g., risk differences, 1.8% [95% CI, −1.5%, 5.0%] and −4.5% [95% CI, −6.6%, −2.4%], respectively). We conclude that selection bias can have a major effect on an IV analysis, and further research is needed on how to conduct sensitivity analyses when selection depends on unmeasured data.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1097/ede.0000000000000972

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • A final important source of bias in MR, and indeed all studies of observational data, is selection bias.

    “A final important source of bias in MR, and indeed all studies of observational data, is selection bias.64,65”

    From Mendelian randomization (2022) · cites this paper as [64]

  • Selection bias can arise in MR studies if an individual's exposure and outcome values affect their participation.

    “Another type of bias that can arise in MR studies that cannot be easily corrected for is selection bias64 In an MR study, an example of selection bias would be if an individual’s exposure and outcome values affected their participation.57”

    From Mendelian randomization (2022) · cites this paper as [64]

  • Case-only study designs may be severely compromised by collider bias, which must be taken into account in data analysis.

    “Importantly, case-only study designs may be severely compromised by collider bias[[G] 56,64, which must be taken into account in data analysis185.”

    From Mendelian randomization (2022) · cites this paper as [64]

  • Population structure can give rise to genetic associations due to differences in the frequency of a variant and the distribution of a trait across the population.

    “Population structure can give rise to genetic associations due to differences in the frequency of a variant and the distribution of a trait across the population (such as latitude in Europe, which correlates with allele frequencies for lactase persistence variants and milk consumption 49 ).”

    From Guidelines for performing Mendelian randomization investigations (2020) · cites this paper as [49]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 45 references couldn’t be matched to a known paper.

Research works printed but not linked: 1

  1. [27]Uddin MJ Groenwold RH Ton de Boer Belitser SV Roes KC Klungel OH Instrumental variable analysis in epidemiologic studies: An overview of the estimation methods. Pharm Anal Acta. 2015; 6: 1– 9.

Cited by

Sorted by citations

Related

Authors
Hughes, R. A., Davies, N. M., Davey Smith, G., & Tilling, K.
Affiliations
  • University of Bristol (GB)
  • Population Health Sciences, Bristol Medical School, University of Bristol, Bristol, United Kingdom
Corresponding author
Hughes, Rachael A.
ORCID
Venue
Epidemiology
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2019-05
Volume
30
Issue
3
Pages
350-357
ISSN
1044-3983 (ISSN-L)
DOI
10.1097/ede.0000000000000972
PMC
PMC6525095
OpenAlex
W2897719756
Cited by
89
References
45
Citations by year
2026: 6 · 2025: 4 · 2024: 11 · 2023: 10 · 2022: 20 · 2021: 14 · 2020: 9 · 2019: 12 · 2018: 2 · 2017: 1
FWCI
10.90
Type
journal article
Language
en
Open access
Licence
Locations
  • Epidemiology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Bristol Research (University of Bristol) (publishedVersion, cc-by)
Funders
  • Wellcome Trust
  • University of Bristol
  • Elizabeth Blackwell Institute for Health Research, University of Bristol
  • Medical Research Council (MC_UU_00011/3, MC_UU_00011/1)
  • Economic and Social Research Council (ES/N000757/1)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
Keywords
selection bias, instrumental variables, two-stage least squares, directed acyclic graphs, research participation, causal effect estimation, UK Biobank, school attendance, smoking initiation, sensitivity analysis
MeSH terms
Epidemiologic Methods, Humans, Selection Bias, Causality, Confounding Factors, Epidemiologic, Treatment Outcome

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