CoChat
Sign Up
Cited by 291Advanced Causal Inference TechniquesHIV/AIDS Research and InterventionsStatistical Methods in Clinical Trials

Regression Discontinuity Designs in Epidemiology: Causal Inference Without Randomized Trials

Open access
Bor, Jacob, Moscoe, Ellen, Mutevedzi, Portia, Newell, Marie-Louise, Bärnighausen, Till·2014·Epidemiology
DOI 10.1097/ede.0000000000000138PMC PMC4162343
Open this paper in CoChat — free account

Abstract

When patients receive an intervention based on whether they score below or above some threshold value on a continuously measured random variable, the intervention will be randomly assigned for patients close to the threshold. The regression discontinuity design exploits this fact to estimate causal treatment effects. In spite of its recent proliferation in economics, the regression discontinuity design has not been widely adopted in epidemiology. We describe regression discontinuity, its implementation, and the assumptions required for causal inference. We show that regression discontinuity is generalizable to the survival and nonlinear models that are mainstays of epidemiologic analysis. We then present an application of regression discontinuity to the much-debated epidemiologic question of when to start HIV patients on antiretroviral therapy. Using data from a large South African cohort (2007-2011), we estimate the causal effect of early versus deferred treatment eligibility on mortality. Patients whose first CD4 count was just below the 200 cells/μL CD4 count threshold had a 35% lower hazard of death (hazard ratio = 0.65 [95% confidence interval = 0.45-0.94]) than patients presenting with CD4 counts just above the threshold. We close by discussing the strengths and limitations of regression discontinuity designs for epidemiology.

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.0000000000000138

Cites

51 of 52 references verified1 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?

  • Fuzzy regression discontinuity and instrumental variables estimate the complier average causal effect (CACE), the effect of the intervention on those who comply with their allocation; under certain assumptions, the CACE is equivalent to the ITT effect divided by the proportion of compliers.

    “Some methods, such as fuzzy regression discontinuity (RD) and instrumental variables (IVs), estimate a different effect, the complier average causal effect (CACE), which is the effect of the intervention on those who comply with their allocation into the control or intervention group (11). Under certain assumptions, the CACE is equivalent to the ITT effect divided by the proportion of compliers.”

    From Natural Experiments: An Overview of Methods, Approaches, and Contributions to Public Health Intervention Research (2017) · cites this paper as [11]

  • The regression discontinuity design relies on the assumption that units with values of the assignment variable just above or below the cutoff for entitlement are similar in other respects, especially if there is random error in the assignment variable.

    “RD is based on the insight that units with values of the assignment variable just above or below the cutoff for entitlement will be similar in other respects, especially if there is random error in the assignment variable (11).”

    From Natural Experiments: An Overview of Methods, Approaches, and Contributions to Public Health Intervention Research (2017) · cites this paper as [11]

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

Research works printed but not linked: 4

  1. [6]Trochim W. Research Design for Program Evaluation: The Regression Discontinuity Design 1984 Beverly Hills, CA Sage Publications
  2. [7]Trochim W. Sechrest L Perrin E Bunker J The Regression Discontinuity Design. In: Agency for Health Care Policy and Research Conference Proceedings: Research Methodology: Strengthening Causal Interpretations of Nonexperimental Data 1990 Washington, D.C.: U.S. Department of Health and Human Services 119 140
  3. [19]Bor J Cash transfers and teen pregnancy in an HIV endemic setting: a regression discontinuity study. In: Essays on the Economics of HIV/AIDS in Rural South Africa [dissertation] 2013 Boston: Harvard University, School of Public Health 91 150
  4. [53]Luft HS The applicability of the regression discontinuity design in health services research. In: Agency for Health Care Policy and Research Conference Proceedings: Research Methodology: Strengthening Causal Interpretations of Nonexperimental Data 1990 Washington, DC: U.S. Department of Health and Human Services 140 143

Cited by

Sorted by citations

Related

Authors
Bor, J., Moscoe, E., Mutevedzi, P., Newell, M.-L., & Bärnighausen, T.
Affiliations
  • Boston University (US)
  • Harvard University (US)
  • University of Southampton (GB)
Corresponding author
Bor, Jacob
ORCID
Venue
Epidemiology
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2014-09
Volume
25
Issue
5
Pages
729-737
ISSN
1044-3983 (ISSN-L)
DOI
10.1097/ede.0000000000000138
PMC
PMC4162343
OpenAlex
W1989279315
Cited by
291
References
52
Citations by year
2026: 15 · 2025: 29 · 2024: 25 · 2023: 21 · 2022: 29 · 2021: 30 · 2020: 32 · 2019: 22 · 2018: 27 · 2017: 20 · 2016: 20 · 2015: 17 · 2014: 4
FWCI
21.23
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Epidemiology (publishedVersion, cc-by)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
  • ePrints Soton (University of Southampton) (acceptedVersion)
  • Digital Access to Scholarship at Harvard (DASH) (Harvard University) (submittedVersion, cc-by)
Funders
  • United States Agency for International Development
  • Wellcome Trust (097410)
  • National Institutes of Health (5r01mh083539-04)
  • National Institute of Mental Health (R01-MH083539, 1R01MH083539-01)
  • Eunice Kennedy Shriver National Institute of Child Health and Human Development (R01HD058482)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
  • Health Sciences › Medicine › Infectious Diseases › HIV/AIDS Research and Interventions
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
Keywords
regression discontinuity design, causal inference, treatment effect estimation, HIV, antiretroviral therapy, CD4 count, survival analysis, nonlinear models, mortality
MeSH terms
Data Interpretation, Statistical, Drug Administration Schedule, Humans, Regression Analysis, Models, Statistical, Cohort Studies, Epidemiologic Research Design, HIV Infections, Causality, Treatment Outcome, CD4 Lymphocyte Count, Anti-HIV Agents

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