The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Interaction as Departure from Additivity in Case-Control Studies: A Cautionary Note
Abstract
It has been argued that assessment of interaction should be based on departures from additive rates or risks. The corresponding fundamental interaction parameter cannot generally be estimated from case-control studies. Thus, surrogate measures of interaction based on relative risks from logistic models have been proposed, such as the relative excess risk due to interaction (RERI), the attributable proportion due to interaction (AP), and the synergy index (S). In practice, it is usually necessary to include covariates such as age and gender to control for confounding. The author uncovers two problems associated with surrogate interaction measures in this case: First, RERI and AP vary across strata defined by the covariates, whereas the fundamental interaction parameter is unvarying. S does not vary across strata, which suggests that it is the measure of choice. Second, a misspecification problem implies that measures based on logistic regression only approximate the true measures. This problem can be rectified by using a linear odds model, which also enables investigators to test whether the fundamental interaction parameter is zero. A simulation study reveals that coverage is much improved by using the linear odds model, but bias may be a concern regardless of whether logistic regression or the linear odds model is used.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The synergy index is also sometimes considered6 (which is the ratio of the extent to which the risk of the doubly exposed group exceeds 1 to the extent to which the sum of the singly exposed groups exceeds 1).”
From Recommendations for presenting analyses of effect modification and interaction (2012) · cites this paper as [6]
In the citing paper
“If additional covariates are included into the model, RERI may vary across levels of those covariates.24”
From Understanding of interaction (subgroup) analysis in clinical trials (2019) · cites this paper as [24]
Citations
Cites
Approximation Theorems of Mathematical Statistics
Serfling, R. J. (1980) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316481 · Cited by 5,851
Lewis, J. A., & Finney, D. (1972) · Applied Statistics · doi:10.2307/2346498 · Cited by 2,665 · cited 1×
“For rare outcomes, this notion of interaction follows from probabilistic independence, as embodied in the classical toxicologic notion of “simple independent action” discussed by Finney (8).”
BackgroundConfidence interval estimation of interaction
Hosmer, D. W., & Lemeshow, S. (1992) · Epidemiology · doi:10.1097/00001648-199209000-00012 · Cited by 1,239 · cited 2×
“Ninety-five percent confidence intervals for all measures are obtained as described by Hosmer and Lemeshow (9).”
MethodROTHMAN, K. J., GREENLAND, S., & WALKER, A. M. (1980) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a113015 · Cited by 859
THE ESTIMATION OF SYNERGY OR ANTAGONISM1
ROTHMAN, K. J. (1976) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a112252 · Cited by 333 · cited 1×
“On the basis of these observations, Rothman (1, 2) suggested a synergy index (S) which can be used in casecontrol studies to measure interaction as departure from additive risks.”
BackgroundConfidence intervals for measures of interaction
Assmann, S. F., Hosmer, D. W., Lemeshow, S., & Mundt, K. A. (1996) · Epidemiology · doi:10.1097/00001648-199605000-00012 · Cited by 262 · cited 1×
“(12), where the investigation was limited to coverage of confidence intervals for RERI and AP in models without additional covariates.”
BackgroundSYNERGY AND ANTAGONISM IN CAUSE-EFFECT RELATIONSHIPS1
ROTHMAN, K. J. (1974) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a121626 · Cited by 250 · cited 2×
“b3 = RD11 – RD10 – RD01 = R11 – R10 – R01 + R00, (1)”
BackgroundINTERACTION OF ALCOHOL AND TOBACCO IN LARYNGEAL CANCER
Flanders, W. D., & Rothman, K. J. (1982) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a113315 · Cited by 132 · cited 1×
“An exception is Flanders and Rothman (10), who suggested a likelihood approach to estimating S from stratified case-control data.”
BackgroundSome Results on the Estimation of Logistic Models Based on Retrospective Data
Farewell, V. T. (1979) · Biometrika · doi:10.1093/biomet/66.1.27 · Cited by 98 · cited 1×
“Importantly, the logistic model can be employed for casecontrol designs under reasonable assumptions (13).”
MethodINTERACTION BETWEEN DISCRETE CAUSES
Koopman, J. S. (1981) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a113153 · Cited by 66
Cited by
Bauer, G. R. (2014) · Social Science & Medicine · doi:10.1016/j.socscimed.2014.03.022 · Cited by 1,620
“It is possible, and in fact not difficult, to construct measures of additive-scale interaction and their confidence intervals from multiplicative-scale models (Skrondal, 2003; Greenland et al., 2008; Zou, 2008), and these may be of use to intersectionality researchers.”
BackgroundRecommendations for presenting analyses of effect modification and interaction
Knol, M. J., & VanderWeele, T. J. (2012) · International Journal of Epidemiology · doi:10.1093/ije/dyr218 · Cited by 1,494
VanderWeele, T. J., & Knol, M. J. (2014) · Epidemiologic Methods · doi:10.1515/em-2013-0005 · Cited by 1,127
“We may have RERI RR larger in one of two subpopulations, but the additive interaction for risks, p 11 À p 10 À p 01 þ p 00 , may be larger in the other; this is because the baseline risks, p 00 , may differ and RERI RR depends on the baseline risk (Skrondal, 2003).”
BackgroundEstrogen plus progestin and risk of venous thrombosis
Cushman, M. (2004) · JAMA · doi:10.1001/jama.292.13.1573 · Cited by 632
“To provide additional insight into the joint relationship of each genetic polymorphism and treatment with VT risk, we also tested an additive odds ratio model using a certain synergy index.(22) Under an additive model, the increment above unity in the odds ratio for hormone therapy and a polymorphism combined is the s…”
MethodTest for additive interaction in proportional hazards models
Li, R., & Chambless, L. (2007) · Annals of Epidemiology · doi:10.1016/j.annepidem.2006.10.009 · Cited by 548
Metadata
- Authors
- Skrondal, A.
- Affiliations
- Norwegian Institute of Public Health (NO)
- Corresponding author
- Skrondal, A.
- ORCID
- Skrondal, A.
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2003-08-01
- Volume
- 158
- Issue
- 3
- Pages
- 251-258
- ISSN
- 0002-9262 (ISSN-L)
- OpenAlex
- W1996813536
- Cited by
- 180
- References
- 13
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 8 · 2023: 7 · 2022: 12 · 2021: 9 · 2020: 5 · 2019: 6 · 2018: 7 · 2017: 6 · 2016: 7 · 2015: 6 · 2014: 13 · 2013: 8 · 2012: 17
- FWCI
- 3.77
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- American Journal of Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- London School of Economics and Political Science Research Online (London School of Economics and Political Science) (acceptedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Keywords
- interaction, case-control study, additivity, relative excess risk due to interaction, synergy index, logistic regression, model misspecification, confounding, confidence interval coverage
- MeSH terms
- Humans, Regression Analysis, Research Design, Reproducibility of Results, Models, Statistical, Odds Ratio, Epidemiologic Studies, Case-Control Studies
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Interaction as Departure from Additivity in Case-Control Studies: A Cautionary Note. https://app.cochat.ai/papers/10.1093/aje/kwg113
- The paper
- Skrondal, A. (2003). Interaction as Departure from Additivity in Case-Control Studies: A Cautionary Note. American Journal of Epidemiology. https://doi.org/10.1093/aje/kwg113
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.