Causal Interactions in the Proportional Hazards Model
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
The paper relates estimation and testing for additive interaction in proportional hazards models to causal interactions within the counterfactual framework. A definition of a causal interaction for time-to-event outcomes is given that generalizes existing definitions for dichotomous outcomes. Conditions are given concerning the relative excess risk due to interaction in proportional hazards models that imply the presence of a causal interaction at some point in time. Further results are given that allow for assessing the range of times and baseline survival probabilities for which parameter estimates indicate that a causal interaction is present, and for deriving lower bounds on the prevalence of such causal interactions. An interesting feature of the time-to-event setting is that causal interactions can disappear as time progresses, ie, whether a causal interaction is present depends on the follow-up time. The results are illustrated by hypothetical and data analysis examples.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“When absolute risks are not reported, when treatment effects are derived from multivariable models (ie treatment effects adjusted for other covariates), or when interaction between treatment and a continuous factor is considered, additive interaction can be assessed using relative excess risk due to interaction (RERI) and synergy index.”
From Understanding of interaction (subgroup) analysis in clinical trials (2019) · cites this paper as [19]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This same tool could also be used in conjunction with a Cox proportional hazards model to produce measures of additive interaction,23,24 and to calculate additive interaction between continuous exposures.25”
From Recommendations for presenting analyses of effect modification and interaction (2012) · cites this paper as [24]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Marginal Structural Models and Causal Inference in Epidemiology
Robins, J. M., Hernán, M. Á., & Brumback, B. (2000) · Epidemiology · doi:10.1097/00001648-200009000-00011 · Cited by 5,581
ROTHMAN, K. J. (1976) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a112335 · Cited by 776
Test 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 · cited 10×
“t; G, E, C 0 t e 1G 2E 3GE k 1 n kCk, (1)”
InfluentialThe 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 · cited 5×
“In practice, one could use the parameter estimates for ( 1, 2, 3) and apply Result 3 to derive a range of values of stc for which there is evidence of causal interaction by conducting a numerical search evaluating the expression in (2) for many possible values of stc to generate the range for which the inequality is s…”
InfluentialSelf-citationSufficient cause interactions and statistical interactions
VanderWeele, T. J. (2009) · Epidemiology · doi:10.1097/ede.0b013e31818f69e7 · Cited by 163
Self-citationEmpirical and counterfactual conditions for sufficient cause interactions
Vanderweele, T. J., & Robins, J. M. (2008) · Biometrika · doi:10.1093/biomet/asm090 · Cited by 103 · cited 2×
“The negation of the expression in (3), ie, {stc exp 1 stc exp 2 stc exp 1 2 3 1}, is a lower bound on the prevalence of individuals exhibiting a causal interaction at time t in strata C c without assumptions about monotonicity.”
Self-citationMarginal Structural Models for Sufficient Cause Interactions
VanderWeele, T. J., Vansteelandt, S., & Robins, J. M. (2010) · American Journal of Epidemiology · doi:10.1093/aje/kwp396 · Cited by 52
Self-citation
Research works printed but not linked: 1
- Andersen PK “Biological” interactions from a statistical point of view. Abstract Second International Biometric Society Channel Network Conference Ghent, Belgium April 6, 2009
Cited by
Recommendations 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
Self-citationVanderWeele, T. J., & Knol, M. J. (2014) · Epidemiologic Methods · doi:10.1515/em-2013-0005 · Cited by 1,127
“…occurs if both exposures are present but not if just one or the other is present) on the other, and finally, (iii) " biological " or " functional " interaction in which the two exposures physically interact to bring about the outcome (Phillips, 2008; Cordell, 2009; VanderWeele, 2010a, 2011a).”
BackgroundSelf-citationCrump, C., Sundquist, J., Winkleby, M. A., & Sundquist, K. (2019) · BMJ · doi:10.1136/bmj.l1346 · Cited by 265
Association of Preterm Birth With Risk of Ischemic Heart Disease in Adulthood
Crump, C., Howell, E. A., Stroustrup, A., McLaughlin, M. A., Sundquist, J., & Sundquist, K. (2019) · JAMA Pediatrics · doi:10.1001/jamapediatrics.2019.1327 · Cited by 258
A Three-way Decomposition of a Total Effect into Direct, Indirect, and Interactive Effects
VanderWeele, T. J. (2013) · Epidemiology · doi:10.1097/ede.0b013e318281a64e · Cited by 242
Self-citationGestational age at birth and mortality from infancy into mid-adulthood: a national cohort study
Crump, C., Sundquist, J., Winkleby, M. A., & Sundquist, K. (2019) · The Lancet Child & Adolescent Health · doi:10.1016/s2352-4642(19)30108-7 · Cited by 158
Preterm birth and risk of type 1 and type 2 diabetes: a national cohort study
Crump, C., Sundquist, J., & Sundquist, K. (2020) · Diabetologia · doi:10.1007/s00125-019-05044-z · Cited by 125
Understanding of interaction (subgroup) analysis in clinical trials
Brankovic, M., Kardys, I., Steyerberg, E. W., Lemeshow, S., Markovic, M., Rizopoulos, D., & Boersma, E. (2019) · European Journal of Clinical Investigation · doi:10.1111/eci.13145 · Cited by 130
Association of Preterm Birth With Long-term Risk of Heart Failure Into Adulthood
Crump, C., Groves, A., Sundquist, J., & Sundquist, K. (2021) · JAMA Pediatrics · doi:10.1001/jamapediatrics.2021.0131 · Cited by 126
Crump, C., Sundquist, J., McLaughlin, M. A., Dolan, S. M., Govindarajulu, U., Sieh, W., & Sundquist, K. (2023) · BMJ · doi:10.1136/bmj-2022-072112 · Cited by 109
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
Timpka, S., Stuart, J. J., Tanz, L. J., Rimm, E. B., Franks, P. W., & Rich-Edwards, J. W. (2017) · BMJ · doi:10.1136/bmj.j3024 · Cited by 119
Adverse Pregnancy Outcomes and Long-Term Mortality in Women
Crump, C., Sundquist, J., & Sundquist, K. (2024) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2024.0276 · Cited by 109
Risk of hypertension into adulthood in persons born prematurely: A national cohort study
Crump, C., Sundquist, J., & Sundquist, K. (2020) · European Heart Journal · doi:10.1093/eurheartj/ehz904 · Cited by 93
“Sex differences were assessed by performing sex-stratified analyses and examining interactions between gestational age at birth and sex on both the additive and multiplicative scale.(28) The proportional hazards assumption was assessed by examining log–log plots(29) and was met in each model.”
MethodSheridan, P. E., Ilango, S. D., Bruckner, T. A., Wang, Q., Basu, R., & Benmarhnia, T. (2019) · American Journal of Epidemiology · doi:10.1093/aje/kwz120 · Cited by 73
Pre-Term Delivery and Risk of Ischemic Heart Disease in Women
Crump, C., Sundquist, J., Howell, E. A., McLaughlin, M. A., Stroustrup, A., & Sundquist, K. (2020) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2020.04.072 · Cited by 62
“Third, interactions were explored between pregnancy duration and preeclampsia or fetal growth restriction (major causes of medically indicated preterm birth) in relation to IHD risk on both the additive and multiplicative scale (19).”
BackgroundPreterm delivery and long term mortality in women: national cohort and co-sibling study
Crump, C., Sundquist, J., & Sundquist, K. (2020) · BMJ · doi:10.1136/bmj.m2533 · Cited by 60
Association of preterm birth with lipid disorders in early adulthood: A Swedish cohort study
Crump, C., Sundquist, J., & Sundquist, K. (2019) · PLOS Medicine · doi:10.1371/journal.pmed.1002947 · Cited by 54
Owili, P. O., Muga, M. A., Pan, W., & Kuo, H. (2017) · International Journal of Environmental Health Research · doi:10.1080/09603123.2017.1332347 · Cited by 57
LOPEZ, P. M., Subramanian, S. V., & Schooling, C. M. (2019) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2019.05.005 · Cited by 59
Preterm birth and risk of sleep-disordered breathing from childhood into mid-adulthood
Crump, C., Friberg, D., Li, X., Sundquist, J., & Sundquist, K. (2019) · International Journal of Epidemiology · doi:10.1093/ije/dyz075 · Cited by 50
“Additive interactions were tested using the ‘relative excess risk due to interaction’ (RERI), which is computed for binary variables as: RERIHR 1⁄4 HR11 HR10 – HR01 þ 1.(36,37) Multiplicative interactions were tested using the ratio of HRs: HR11 / (HR10 HR01).”
MethodVanderWeele, T. J., & Knol, M. J. (2011) · American Journal of Epidemiology · doi:10.1093/aje/kwr009 · Cited by 46
Self-citationAirborne mammary carcinogens and breast cancer risk in the Sister Study
Niehoff, N. M., Gammon, M. D., Keil, A. P., Nichols, H. B., Engel, L. S., Sandler, D. P., & White, A. J. (2019) · Environment International · doi:10.1016/j.envint.2019.06.007 · Cited by 44
Hershey, M. S., Martínez‐González, M. Á., Álvarez‐Álvarez, I., Martínez, J. A., & Ruiz‐Canela, M. (2021) · British Journal Of Nutrition · doi:10.1017/s0007114521002877 · Cited by 42
“time and more precise estimates may require very large study populations(70).”
BackgroundBeydoun, M. A., Beydoun, H. A., Kaufman, J. S., An, Y., Resnick, S. M., O'Brien, R., Ferrucci, L., & Zonderman, A. B. (2013) · Journal of the American Geriatrics Society · doi:10.1111/jgs.12156 · Cited by 38
“RERI greater than 1 indicates synergism without needing to assume monotonicity of effects.(43,44)”
BackgroundComparative risk of suicide by specific substance use disorders: A national cohort study
Crump, C., Sundquist, J., Kendler, K. S., Edwards, A. C., & Sundquist, K. (2021) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2021.10.017 · Cited by 39
He, L., Yang, N., Wang, J., Huang, J., Li, W., Xu, L., Ping, F., Li, Y., & Zhang, H. (2021) · Obesity · doi:10.1002/oby.23179 · Cited by 48
“RERI > 0 and < 0 indicated a positive and negative additive interaction, respectively, with RERI = 0 indicating an insignificant additive interaction (22).”
BackgroundPuzhko, S., Roy, É., Jutras‐Aswad, D., Artenie, A. A., Fortier, E., Zang, G., & Bruneau, J. (2017) · International Journal of Drug Policy · doi:10.1016/j.drugpo.2017.05.027 · Cited by 36
Crump, C., Sundquist, J., & Sundquist, K. (2023) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2023.10.008 · Cited by 33
Niehoff, N. M., Terry, M. B., Bookwalter, D. B., Kaufman, J. D., O'Brien, K. M., Sandler, D. P., & White, A. J. (2021) · Cancer Epidemiology Biomarkers & Prevention · doi:10.1158/1055-9965.epi-21-1140 · Cited by 32
“estimated and used to calculate the interaction contrast ratios (ICRs) and 95% CIs (32-34).”
MethodMuga, M. A., Owili, P. O., Hsu, C., & Chao, J. C.-J. (2019) · BMC Public Health · doi:10.1186/s12889-019-7686-0 · Cited by 30
Assessing Causal Mechanistic Interactions: A Peril Ratio Index of Synergy Based on Multiplicativity
Lee, W. (2013) · PLoS ONE · doi:10.1371/journal.pone.0067424 · Cited by 24
“In a recent paper, VanderWeele [27] studied proportional hazards models and made an interesting conclusion that ‘‘causal interactions can disappear as time progresses, ie, whether a causal interaction is present depends on the follow-up time’’.”
BackgroundYang, P., Hou, M., Ou‐Yang, F., Hsieh, T., Lee, Y.-J., Tsai, E., & Wang, T. (2022) · Scientific Reports · doi:10.1038/s41598-022-06709-3 · Cited by 20
Beydoun, M. A., Hooten, N. N., Georgescu, M. F., Beydoun, H. A., Eid, S. M., Kuczmarski, M. F., Evans, M. K., & Zonderman, A. B. (2024) · European Journal of Epidemiology · doi:10.1007/s10654-024-01131-7 · Cited by 16
“Conversion to the additive scale can be implied with equations shown below for the Cox proportional hazards model and the relative excess risk due to interaction (RERI), when both exposures and moderators are binary [42–44].”
BackgroundMethodInfluentialInvited Commentary: The Continuing Need for the Sufficient Cause Model Today
VanderWeele, T. J. (2017) · American Journal of Epidemiology · doi:10.1093/aje/kwx083 · Cited by 16
Self-citationEvaluating Additive Interaction Using Survival Percentiles
Bellavia, A., Bottai, M., & Orsini, N. (2016) · Epidemiology · doi:10.1097/ede.0000000000000449 · Cited by 16
Mortensen, L. M., Hansen, C. P., Overvad, K., Lundbye‐Christensen, S., & Parner, E. T. (2018) · Epidemiologic Methods · doi:10.1515/em-2017-0015 · Cited by 13
Sylvestre, M.-P., Chagnon, M., Wellman, R. J., Dugas, E. N., & O’Loughlin, J. (2018) · American Journal of Epidemiology · doi:10.1093/aje/kwy045 · Cited by 12
Integrated multiple mediation analysis: A robustness‐specificity trade‐off in causal structure
Tai, A., & Lin, S. (2021) · Statistics in Medicine · doi:10.1002/sim.9079 · Cited by 12
Son, H. E., Moon, J.-J., Park, J.-M., Ryu, J. Y., Baek, E., Jeong, J. C., Chin, H. J., Na, K. Y., Chae, D., Han, S. S., et al. (2021) · Kidney Research and Clinical Practice · doi:10.23876/j.krcp.21.111 · Cited by 12
“RERI was calculated as hazard ratio (HR, both AKI and AHF) − HR (AKI alone) − HR (AHF alone) + 1 [17,18].”
MethodJohnson, C. E., Alberg, A. J., Bandera, E. V., Peres, L. C., Akonde, M., Collin, L. J., Coté, M. L., Hastert, T. A., Hébert, J. R., Peters, E. S., et al. (2023) · British Journal of Cancer · doi:10.1038/s41416-023-02385-w · Cited by 11
Zhang, Y., Lee, D. H., Rezende, L. F. M., Ma, Y., & Giovannucci, E. L. (2026) · British Journal of Sports Medicine · doi:10.1136/bjsports-2025-110503 · Cited by 9
“38 In sensitivity analyses, we applied longer lag-time (4, 8-and 12-year) between resistance training and all-cause and cause-specific mortality and evaluated the association separately by sex.”
Scherrer, J. F., Salas, J., Lustman, P. J., Tuerk, P. W., Gebauer, S., Norman, S. B., Schneider, D., Chard, K. M., van den Berk‐Clark, C., Cohen, B. E., et al. (2019) · European Journal of Preventive Cardiology · doi:10.1177/2047487319850717 · Cited by 8
“The joint effects of OAU and PTSD on CVD were tested and the multiplicative interaction was assessed via the ratio and 95% CI of stratum specific hazard ratios while the additive interaction, which is thought to better reflect biological interaction,(18) was tested using the relative excess risk due to interaction (RE…”
MethodSantos‐Pardo, I., Lagerqvist, B., Ritsinger, V., Witt, N., Norhammar, A., & Nyström, T. (2021) · International Journal of Cardiology · doi:10.1016/j.ijcard.2021.02.011 · Cited by 9
Improving interventional causal predictions in regulatory risk assessment
Cox, L. A. (2023) · Critical Reviews in Toxicology · doi:10.1080/10408444.2023.2229923 · Cited by 8
Josey, K., Nethery, R. C., Visaria, A., Bates, B., Gandhi, P., Parthasarathi, A., Rua, M., Robinson, D., & Setoguchi, S. (2023) · BMJ Open · doi:10.1136/bmjopen-2023-072810 · Cited by 8
Air pollution and serious bleeding events in high-risk older adults
Fayyad, R., Josey, K., Gandhi, P., Rua, M., Visaria, A., Bates, B. A., Setoguchi, S., & Nethery, R. C. (2024) · Environmental Research · doi:10.1016/j.envres.2024.118628 · Cited by 6
Crump, C., Sundquist, J., Kendler, K. S., Edwards, A. C., & Sundquist, K. (2021) · International Journal of Epidemiology · doi:10.1093/ije/dyab038 · Cited by 6
“Sex-specific differences were assessed by performing sexstratified analyses and formally testing for interactions between gestational age at birth or fetal growth and sex on the additive and multiplicative scale.(14) The proportional hazards assumption was assessed by examining log-log plots, which showed no substanti…”
MethodNova, A., Fazia, T., & Bernardinelli, L. (2024) · Medicina · doi:10.3390/medicina60071053 · Cited by 4
“More details can be found in [13].”
Neibart, S. S., Malhotra, J. D., Roy, J., Strom, B. L., & Jabbour, S. K. (2023) · Journal of Thoracic Disease · doi:10.21037/jtd-22-1649 · Cited by 5
“RERI was calculated using the coefficients from Cox regression as previously described (34).”
Sufficient Cause Interaction for Time-to-event Outcomes
Stensrud, M. J., Ryalen, P. C., & Røysland, K. (2019) · Epidemiology · doi:10.1097/ede.0000000000000958 · Cited by 1
“1 | | − − x X x C c L l i i i i 1 2 2 , = , = , = ) , (9)”
The effect of hereditary and lifestyle risk factors on colorectal adenoma and colorectal cancer risk
Pham, T. T. (2024) · Digital Access to Scholarship at Harvard (DASH) (Harvard University)
Metadata
- Authors
- VanderWeele, T. J.
- Affiliations
- Harvard University (US)
- Corresponding author
- VanderWeele, Tyler J.
- Venue
- Epidemiology
- Published
- 2011-09
- Volume
- 22
- Issue
- 5
- Pages
- 713-717
- ISSN
- 1044-3983 (ISSN-L)
- PMC
- PMC3150431
- OpenAlex
- W2088065266
- Cited by
- 53
- References
- 7
- Citations by year
- 2026: 1 · 2024: 4 · 2023: 7 · 2022: 2 · 2021: 9 · 2020: 2 · 2019: 14 · 2018: 2 · 2017: 4 · 2016: 1 · 2014: 1 · 2013: 3 · 2012: 2
- FWCI
- 1.96
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institute of Environmental Health Sciences (ES017876, R01ES017876, R56ES017876)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Keywords
- causal interaction, proportional hazards model, additive interaction, counterfactual framework, time-to-event outcomes, relative excess risk due to interaction, time-varying interactions
- MeSH terms
- Causality, Proportional Hazards Models
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
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.