Interaction Reaction
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
A rose by any other name may smell as sweet, but this is no license to ignore the importance of precise language in scientific writing. Many of the technical terms used in epidemiology have alternate meanings in common parlance. Statisticians are particularly clever at transforming mundane words into apt metaphors (eg, “bootstrap,” “kernel,” “jackknife”). But, multiple meanings can also create confusion. Our use of the word “bias” frequently raises eyebrows among nonepidemiologists. To “confound” means something different in ordinary English than in the context of epidemiology. The term “interaction” is a minefield of potential misunderstanding. Its use in statistical modeling is thoroughly entrenched and yet distinct from its connotations in both epidemiology and in common English conversation. What statisticians mean is simply a deviation from the specified model form, a deviation that can be accommodated by a product term between 2 or more right-hand-side variables. These variables do not “interact” in any of the meanings suggested by English dictionaries. It is at the boundary of statistics and epidemiology—that is, in our interpretation of statistical models as causal or mechanistic statements—that this miscommunication is most dangerous. And yet it is causal interpretation that motivates most epidemiologic investigation. As Knol et al point out in this issue of the journal,1 the presentation and discussion of interaction in the medical and epidemiologic literature is woefully inadequate. What can be done to improve this? Greenland has recently recommended that we abandon the word “interaction” altogether.2 This proposal is not unreasonable (and can be adopted by any sympathetic author). It is not, however, a solution that the editors of Epidemiology are inclined to advocate. Statisticians are unlikely to alter their deep-rooted usage, and the potential for misunderstanding will persist. We prefer instead that authors clarify their use of that ambiguous word “interaction” by adding a qualifier. Interactions can be “additive” or “multiplicative” or, better yet, described as deviations from additive or multiplicative joint effects. Deviations from additivity are of interest from the perspective of public health or health services, because they identify subpopulations that would most benefit from potential interventions.2 Deviation from multiplicativity is convenient to compute but not as easy to defend substantively. Although multiplicative interaction can have important epidemiologic implications,3 such interaction has little direct bearing on “synergism” in the biologic sense, or on interdependence of latent causal types–at least not without important additional assumptions.4,5 Where a mechanistic interpretation is intended, as in the phrase “gene–environment interaction,” Greenland's more radical suggestion to dump the word entirely is perhaps justified. Beyond simply qualifying the type of interaction being discussed, there are ways to improve practice along the lines suggested by Knol et al.1 The somewhat arbitrary choice of model form determines the default scale for joint effects.6 Analysts with limited power and a passion for parsimony will tend toward the joint-effects model suggested by their selected link function rather than by their data.2 Greenland's suggestion to prune our models less zealously would give data a greater role in determining the fit. The modeled values can then be reported more completely, allowing readers to examine joint effects on both common scales.1 At Epidemiology, we encourage authors who report “interaction” to present the individual effects of both of the exposures and their joint effects–each relative to the group not exposed to either factor. An equally welcome approach would be to report the relevant parameters from a regression model (ie, the individual coefficients for both exposures and their product term). The most egregious error described by Knol et al is the declaration of effect heterogeneity when the estimated effect is “statistically significant” in one subgroup but not “statistically significant” in another. Although Knol et al found few articles in the selected journals that made this inference overtly, this illogic is not uncommon in the wider literature.7 Our long-standing policy of discouraging significance tests helps avoid this error (among others).8 Nonetheless, we began to allow P values for interaction on the basis of several arguments, one being that there is no relevant parameter of interest to report.9 Recent articles on interaction now lead us to conclude that we can do better. VanderWeele4 has demonstrated that the coefficient on the product term is indeed a parameter of interest when considering joint effects. Its sign and magnitude can have important implications beyond its (statistical) “significance.” Authors can expect to see evidence of our evolving perspective on these issues in their (editorial) interactions with the journal.
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 concept of disease interaction has had a long and controversial history in the epidemiologic literature (Blot & Day, 1979; Greenland, 2009; Kaufman, 2009; Kupper & Hogan, 1978; Rothman, 1974, 1976a; Rothman, Greenland, & Walker, 1980; Saracci, 1980; Siemiatycki & Thomas, 1981; VanderWeele, 2009a; Walter & Holford, 1978).”
From Syndemics of psychosocial problems and HIV risk: A systematic review of empirical tests of the disease interaction concept (2015) · cites this paper as Kaufman, 2009
Citations
Cites
The Difference Between “Significant” and “Not Significant” is not Itself Statistically Significant
Gelman, A., & Stern, H. (2006) · The American Statistician · doi:10.1198/000313006x152649 · Cited by 1,407 · cited 1×
“Although Knol et al found few articles in the selected journals that made this inference overtly, this illogic is not uncommon in the wider literature.(7) Our long-standing policy of discouraging significance tests helps avoid this error (among others).”
BackgroundDrinking Water Source and Chlorination Byproducts II. Risk of Colon and Rectal Cancers
Hildesheim, M. E., Cantor, K. P., Lynch, C. F., Dosemeci, M., Lubin, J., Alavanja, M., & Craun, G. (1998) · Epidemiology · doi:10.1097/00001648-199801000-00008 · Cited by 357
Interactions in epidemiology: relevance, identification, and estimation
Greenland, S. (2009) · Epidemiology · doi:10.1097/ede.0b013e318193e7b5 · Cited by 204 · cited 3×
“What can be done to improve this? Greenland has recently recommended that we abandon the word “interaction” altogether.(2) This proposal is not unreasonable (and can be adopted by any sympathetic author).”
BackgroundInfluentialThe identification of synergism in the sufficient-component-cause framework
VanderWeele, T. J., & Robins, J. M. (2007) · Epidemiology · doi:10.1097/01.ede.0000260218.66432.88 · Cited by 183
Effect modification and the limits of biological inference from epidemiologic data
Thompson, W. D. (1991) · Journal of Clinical Epidemiology · doi:10.1016/0895-4356(91)90033-6 · Cited by 168
Sufficient cause interactions and statistical interactions
VanderWeele, T. J. (2009) · Epidemiology · doi:10.1097/ede.0b013e31818f69e7 · Cited by 163 · cited 1×
“sense, or on interdependence of latent causal types–at least not without important additional assumptions.(4,5) Where a mechanistic interpretation is intended, as in the phrase”
BackgroundWhen One Depends on the Other: Reporting of Interaction in Case-Control and Cohort Studies
Knol, M. J., Egger, M., Scott, P., Geerlings, M. I., & Vandenbroucke, J. P. (2009) · Epidemiology · doi:10.1097/ede.0b013e31818f6651 · Cited by 113 · cited 3×
“The modeled values can then be reported more completely, allowing readers to examine joint effects on both common scales.(1) At EPIDEMIOLOGY, we encourage authors who report “interaction” to present the individual effects of both of the exposures and their joint effects– each relative to the group not exposed to eithe…”
BackgroundMethodInfluentialIt’s Time to Rehabilitate the P-Value
Weinberg, C. R. (2001) · Epidemiology · doi:10.1097/00001648-200105000-00004 · Cited by 66
SHOULD WE ABANDON STATISTICAL MODELING ALTOGETHER?1
VANDENBROUCKE, J. P. (1987) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a114640 · Cited by 39 · cited 1×
“The somewhat arbitrary choice of model form determines the default scale for joint effects.(6) Analysts with limited power”
Background
Research works printed but not linked: 1
- Lang, 1998, That confounded P-value., Epidemiology, 9, 7, 10.1097/00001648-199801000-00004 · DOI
Cited by
Tsai, A. C., & Burns, B. F. O. (2015) · Social Science & Medicine · doi:10.1016/j.socscimed.2015.06.024 · Cited by 227
“…concept of disease interaction has had a long and controversial history in the epidemiologic literature (Blot & Day, 1979; Greenland, 2009; Kaufman, 2009; Kupper & Hogan, 1978; Rothman, 1974, 1976a; Rothman, Greenland, & Walker, 1980; Saracci, 1980; Siemiatycki & Thomas, 1981;…”
MethodQin, L., Knol, M. J., Corpeleijn, E., & Stolk, R. P. (2010) · European Journal of Epidemiology · doi:10.1007/s10654-009-9395-y · Cited by 126
Neighborhood Effects on Health: Correcting Bias From Neighborhood Effects on Participation
Chaix, B., Billaudeau, N., Thomas, F., Havard, S., Evans, D., Kestens, Y., & Bean, K. (2010) · Epidemiology · doi:10.1097/ede.0b013e3181fd2961 · Cited by 117
Additive Interaction in Survival Analysis: Use of the Additive Hazards Model
Rod, N. H., Lange, T., Andersen, I., Marott, J. L., & Diderichsen, F. (2012) · Epidemiology · doi:10.1097/ede.0b013e31825fa218 · Cited by 131
Transportation noise and annoyance related to road traffic in the French RECORD study
Méline, J. C., Hulst, A. V., Thomas, F., Karusisi, N., & Chaix, B. (2013) · International Journal of Health Geographics · doi:10.1186/1476-072x-12-44 · Cited by 81
“As shown in Table 5, we documented interactions on the multiplicative scale between the effects on annoyance of road traffic noise estimated in the residential neighborhood or at the place of residence and of neighborhood income or neighborhood education [27].”
Method
Metadata
- Authors
- Kaufman, J. S.
- Affiliations
- McGill University (CA)
- Corresponding author
- Kaufman, Jay S.
- ORCID
- Kaufman, Jay S.
- Venue
- Epidemiology
- Published
- 2009-03
- Volume
- 20
- Issue
- 2
- Pages
- 159-160
- ISSN
- 1044-3983 (ISSN-L)
- OpenAlex
- W4255644998
- Cited by
- 27
- References
- 9
- Citations by year
- 2026: 2 · 2025: 1 · 2022: 1 · 2020: 1 · 2018: 1 · 2017: 1 · 2016: 1 · 2015: 2 · 2013: 6 · 2012: 3
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (2r24hd050924-06)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (R24 HD-050924)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Library and Information Sciences › Academic Writing and Publishing
- Keywords
- terminology, statistical modeling, causal interpretation, multiplicative interaction, additive interaction, interaction terms, gene-environment interaction, confounding, bias, science communication, mechanistic interpretation, synergistic effect
- MeSH terms
- Terminology as Topic, Statistics as Topic, Epidemiologic 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 Reaction. https://app.cochat.ai/papers/10.1097/ede.0b013e318197c0f5
- The paper
- Kaufman, J. S. (2009). Interaction Reaction. Epidemiology. https://doi.org/10.1097/ede.0b013e318197c0f5
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.