The DOI matches its Crossref record; 28 of the 30 references it cites were found in a registry or an index.
The Table 2 Fallacy: Presenting and Interpreting Confounder and Modifier Coefficients
Open accessAbstract
It is common to present multiple adjusted effect estimates from a single model in a single table. For example, a table might show odds ratios for one or more exposures and also for several confounders from a single logistic regression. This can lead to mistaken interpretations of these estimates. We use causal diagrams to display the sources of the problems. Presentation of exposure and confounder effect estimates from a single model may lead to several interpretative difficulties, inviting confusion of direct-effect estimates with total-effect estimates for covariates in the model. These effect estimates may also be confounded even though the effect estimate for the main exposure is not confounded. Interpretation of these effect estimates is further complicated by heterogeneity (variation, modification) of the exposure effect measure across covariate levels. We offer suggestions to limit potential misunderstandings when multiple effect estimates are presented, including precise distinction between total and direct effect measures from a single model, and use of multiple models tailored to yield total-effect estimates for covariates.
Overview
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.
Integrity signals
Registry
Cites
Statistics
Verification
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.
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
“After controlling for gender and age as potential confounding factors, independent associations between the outcome variables of burnout as well as anxiety/depression and the explanatory variables (i.e., ALTs, psychological flexibility) were examined [58].”
From The mediating role of psychological flexibility in the association of autistic-like traits with burnout and depression in medical students during clinical clerkships in Japan: a university-based cross-sectional study (2023) · cites this paper as [58]
Experimental — accuracy not yet measured
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
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340
Air Pollution and Hospital Admissions for Heart Disease in Eight U.S. Counties
Schwartz, J. D. (1999) · Epidemiology · doi:10.1097/00001648-199901000-00005 · Cited by 3,045
Causal diagrams for empirical research
PEARL, J. (1995) · Biometrika · doi:10.1093/biomet/82.4.669 · Cited by 2,355 · cited 1×
“Model 1 then remains valid for obtaining an unbiased estimate of the total effect of HIV on the log odds of stroke; that is, under model 1, β1 retains its interpretation as the total effect of HIV, as it did under Figure 1, because smoking and age satisfy the back-door criterion for sufficiency for confounding control…”
BackgroundIdentifiability and exchangeability for direct and indirect effects
Robins, J. M., & Greenland, S. (1992) · Epidemiology · doi:10.1097/00001648-199203000-00013 · Cited by 1,793
Self-citationHernan, M. A. (2002) · American Journal of Epidemiology · doi:10.1093/aje/155.2.176 · Cited by 1,445
Statistical modeling: The two cultures
Breiman, L. (2001) · Cited by 1,314
Dose-Response and Trend Analysis in Epidemiology
Greenland, S. (1995) · Epidemiology · doi:10.1097/00001648-199507000-00005 · Cited by 1,086
Self-citationConfounding and Collapsibility in Causal Inference
Greenland, S., Pearl, J., & Robins, J. M. (1999) · Statistical Science · doi:10.1214/ss/1009211805 · Cited by 933 · cited 3×
“represent changes in the log odds of the outcome) and we assume the outcome is uncommon at all covariate levels to avoid complications arising from noncollapsibility of odds ratios (9, 10).”
BackgroundSelf-citationQuantifying Biases in Causal Models: Classical Confounding vs Collider-Stratification Bias
Greenland, S. (2003) · Epidemiology · doi:10.1097/01.ede.0000042804.12056.6c · Cited by 810
Self-citation
Flagged first, then by citations
2 of the 30 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 701–800 of 1,000
Lewer, D., Gilbody, S. M., Lewis, G., Pryce, J., Santorelli, G., Wadman, R., Watmuff, A., & Wright, J. (2024) · Social Psychiatry and Psychiatric Epidemiology · doi:10.1007/s00127-023-02608-8 · Cited by 3
“These associations should be treated with caution because the analysis was not designed to estimate causal effects of these variables, and interpreting these coefficients causally is known as the ‘Table 2 fallacy’ [37].”
Pearce, N. E., & Greenland, S. (2024) · Springer eBooks · doi:10.1007/978-1-4614-6625-3_10-1 · Cited by 3
Self-citationKwiatkowska, R. M., Chatzilena, A., King, J., Clout, M., McGuinness, S., Maskell, N. A., Oliver, J., Challen, R., Hickman, M., Finn, A. H. R., et al. (2024) · BMC Infectious Diseases · doi:10.1186/s12879-024-09425-7 · Cited by 3
Clarifying the Relationship Between Political Consumerism and Political Persuasion Over Time
Scheffauer, R., Medina, L., & de Zúñiga, H. G. (2024) · Political Research Quarterly · doi:10.1177/10659129241266823 · Cited by 3
“Some effects might be direct whereas others are total, as some of the covariates also in fl uence each other over time (i.e., education and income) while also impacting the variables of interest (Keele, Stevenson, and Elwert 2020; Westreich and Greenland 2013).”
Frank, H. A., & Karim, M. E. (2024) · Journal of Asthma · doi:10.1080/02770903.2024.2393677 · Cited by 4
“To avoid the “Table 2 fallacy,” only unadjusted associations are shown for covariates (50).”
Public perception on face mask wearing during COVID-19 pandemic in Malaysia: A cross sectional study
Yusof, M. Z., Fadzil, N. F. Z., Kamaruzi, N. N. N. A., & Ayazi, M. S. S. (2024) · PLoS ONE · doi:10.1371/journal.pone.0303031 · Cited by 4
Shrovnal, J. S., Ray, B. A., Carl, D. D., Shaw, S. L., Sapper, S. A., Zunker, C. A., & Lind, R. A. (2024) · Journal of Great Lakes Research · doi:10.1016/j.jglr.2024.102424 · Cited by 2
Cerrai, S., Carreras, G., Monti, F., Stival, C., Lugo, A., Bosetti, C., Biagioni, S., Fanucchi, T., Gorini, G., Amerio, A., et al. (2024) · Journal of Epidemiology · doi:10.2188/jea.je20230340 · Cited by 3
“50,51 Moreover, despite the limitation of having a reduced number of observations in the two middle COVID-19 waves, the modelling strategy allowed to include all the observations coming from surveys with di ff erent sample sizes in an unbalanced design, without loss of power, and with not equally…”
Uppal, A., Pullen, N., Baysson, H., Schrempft, S., Bouhet, A. R., Zaballa, M.-E., Lamour, J., Nehme, M., Guessous, I., Stringhini, S., et al. (2025) · BMC Public Health · doi:10.1186/s12889-024-21142-z · Cited by 6
Shimizu, A., Maeda, K., Ueshima, J., Ishida, Y., Inoue, T., Murotani, K., Nagano, A., Mori, N., Ohno, T., & Fujisima, I. (2025) · European Journal of Clinical Nutrition · doi:10.1038/s41430-025-01584-3 · Cited by 3
“The estimates of covariates in the multivariate analysis were not shown in the fi gure to account for the fallacy of the estimates [27].”
Checklist for Theoretical Report in Epidemiological Studies (CRT-EE): explanation and elaboration
Filho, B. A. B. D. S., Tritany, É. F., & Struchiner, C. J. (2021) · Physis Revista de Saúde Coletiva · doi:10.1590/s0103-73312021310124 · Cited by 3
Puchades, A., Daniel, R., Geen, J., Peden, J., Lewis, H., & Nnoaham, K. E. (2022) · BMC Public Health · doi:10.1186/s12889-021-12478-x · Cited by 3
“Even with the above concerns aside, additional care must be taken when interpreting the estimated conditional ORs from the logistic regression model results in Table 2, to avoid the so-called Table 2 Fallacy [25].”
BackgroundEarly Life Factors and Eosinophilic Esophagitis
Jensen, E. T., & Gupta, S. K. (2018) · Journal of Pediatric Gastroenterology and Nutrition · doi:10.1097/mpg.0000000000002136 · Cited by 3
“This is a common approach in many observational studies, but one that can significantly introduce bias in observed estimates (9).”
BackgroundA cohort study of two intravenous treatments for iron deficiency in patients with heart failure
Arias-Barrera, C. A., Palacios-Ariza, M. A., Pradilla, I. F., & Álvarez, C. (2019) · Acta cardiologica. Supplementum · doi:10.1080/00015385.2019.1639270 · Cited by 3
Zimmerman, G. M., Douglas, S. D., Turchan, B. S., & Braga, A. A. (2023) · Health & Place · doi:10.1016/j.healthplace.2023.102970 · Cited by 3
Exploring public engagement with missing person appeals on TwitterPreprint
Solymosi, R., Petcu, O., & Wilkinson, J. (2020) · doi:10.31235/osf.io/wugxs · Cited by 3
Subjective Social Status and Allostatic Load among Older People in England. A Longitudinal AnalysisPreprint
Richards, L., Maharani, A., & Präg, P. (2022) · doi:10.31235/osf.io/8459x · Cited by 3
A workflow for causal inference in cross-cultural psychologyPreprint
Bulbulia, J. A. (2022) · doi:10.31234/osf.io/tcrfu · Cited by 3
Psychological predictors of COVID-19 vaccination in New ZealandPreprint
Marques, M. D., Sibley, C. G., Wilson, M., Bulbulia, J. A., Osborne, D., Yogeeswaran, K., Lee, C. H. J., Duck, I. M., Douglas, K. M., & Cichocka, A. K. (2022) · doi:10.31234/osf.io/zkj7u · Cited by 3
Clark, M., Hamad, H. M., Andrews, J. B., Hillis, V., & Mulder, M. B. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.13.527316 · Cited by 3
Methods in Causal Inference Part 1: Causal Diagrams and ConfoundingPreprint
Bulbulia, J. A. (2023) · doi:10.31234/osf.io/b23k7 · Cited by 3
Arning, N., Fryer, H. R., & Wilson, D. J. (2024) · medRxiv · doi:10.1101/2024.01.01.24300687 · Cited by 3
“The direct effect can differ in magnitude and direction to the total effect, and confusing the two is a pitfall known as the Table 2 fallacy (8).”
Bulbulia, J. A., Davis, D. E., Rice, K., Sibley, C. G., & TROUGHTON, G. M. (2024) · doi:10.31234/osf.io/cnphs · Cited by 3
Post-ERCP pneumobilia: the risk of cholangitis and recurrent choledocholithiasis
Ali, F. S., & Thosani, N. C. (2024) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2023.12.032 · Cited by 3
Ani, I., Iyamu, I. O., Akpan, U., Nwanja, E., Onwah, O., Toyo, O., Gana, B., Joseph, U. C. A., Okolo, C., Usang, S., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-5434482/v1 · Cited by 3
Har-Even, A., Lewis, N., Eliash, H., & Sznitman, S. R. (2024) · International Journal of Drug Policy · doi:10.1016/j.drugpo.2024.104654 · Cited by 2
Predictors of Sustainable Investment Motivation: An Interpretable Machine Learning Approach
Sosnovskikh, S., Valko, D., & Meyer-Alten, R. (2025) · Sustainable Development · doi:10.1002/sd.3387 · Cited by 4
Vaman, R. S., Thomas, G. D., Kalyanasundaram, M., Soman, S., Valamparampil, M. J., Suseela, R. P. B., & Murhekar, M. V. (2025) · IJID Regions · doi:10.1016/j.ijregi.2025.100615 · Cited by 2
“For each variable, relevant covariates were identified as confounders by comparing the − 2 log-likelihood ratio values of the models with and without the potential confounders, as per the conceptual framework based on directed acyclic graphs [ 22 ].”
Impact of mental health service use on the HIV care cascade among women
Chawla, S., Kaida, A., Brouillette, M., Kleiner, B., Dubuc, D., Skerritt, L., Burchell, A. N., Rouleau, D., Loutfy, M. R., & de Pokomandy, A. (2025) · HIV Medicine · doi:10.1111/hiv.70008 · Cited by 3
“While there were also statistically significant effect estimates for the covariates, they were excluded from the interpretation due to the potential for confounding [42 – 44].”
McHenry, R. D., Moultrie, C. E., Corfield, A. R., Lone, N., Mitchell, R., Mackay, D., & Pell, J. P. (2025) · British Journal of Anaesthesia · doi:10.1016/j.bja.2025.05.019 · Cited by 2
Political ideology and views toward solar geoengineering in the United States
Magistro, B., Debnath, R., Ebanks, D., Wennberg, P. O., & Alvarez, R. M. (2025) · PLOS Climate · doi:10.1371/journal.pclm.0000643 · Cited by 2
Choi, J., & Garwe, T. (2025) · The Journal of Trauma: Injury, Infection, and Critical Care · doi:10.1097/ta.0000000000004726 · Cited by 2
Conflation of prediction and causality in the TB literature
Romo, M. L., Barcellini, L., Franke, M. F., & Khan, P. Y. (2025) · IJTLD OPEN · doi:10.5588/ijtldopen.25.0142 · Cited by 2
“12 Although all regression coefficients from a predictive study should be presented and interpreted, this is not the case for etiologic studies, which are typically focused on a specific exposure and interpreting coefficients of confounders may lead to incorrect conclusions about their role in the…”
Taylor, D., Roberts, J. L., Rose, V. K., Gyani, A., & Shlonsky, A. (2025) · Children and Youth Services Review · doi:10.1016/j.childyouth.2025.108597 · Cited by 2
van Huizen, R., Annequin, M., Mora, M., Faye, A., Fiorentino, M., Bourrelly, M., Maradan, G., Bérenger, C., Michard, F., Yazdanpanah, Y., et al. (2025) · AIDS Care · doi:10.1080/09540121.2025.2560094 · Cited by 2
“To avoid committing Table Two Fallacy, our adjusted model controlled for the following confounders: age, unstable housing, nationality, monthly revenue, education level, health insurance scheme coverage, and region of medical follow-up (Bandoli et al., 2018; Westreich & Greenland, 2013).”
Stanisavljević, J., Grubor, N. N., Marjanovic, S., Palibrk, I., Bezmarević, M., Veličković, J., Hadžibegović, A., Milenković, M., Ratković, S., & Jovanović, B. (2025) · Nutrients · doi:10.3390/nu17193180 · Cited by 2
“The influence of protein intake was modeled separately to explore its independent relationship with each outcome while accounting for overall caloric intake, in line with best practices to avoid the “Table 2 Fallacy” [23], the mistaken interpretation of adjusted variables as independent exposures.”
Exploring predictors of post-COVID-19 condition among 810 851 individuals in Sweden
Xu, Y., Li, H., Sigström, R., Lundberg, L., Gisslén, M., Larsson, S. B., Nyberg, F., & Bygdell, M. (2025) · Communications Medicine · doi:10.1038/s43856-025-01157-2 · Cited by 2
Likelihood of following a physician prescription to engage in the arts in the US
Fancourt, D. E., Cohen, R., & Sonke, J. K. (2025) · iScience · doi:10.1016/j.isci.2025.113877 · Cited by 2
Brown, S., Hemelrijck, M. V., Price, G. J., Oppong, F. B., Verhoeff, J. J. C., & Finn, C. F. (2025) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2025.111311 · Cited by 4
Regional Factors and Ambulatory Care–Sensitive Condition Hospitalizations in Older Japanese Adults
Abe, K., Ohashi, K., Komoto, S., & Ogasawara, K. (2025) · JAMA Network Open · doi:10.1001/jamanetworkopen.2025.49457 · Cited by 2
Hewins, B., Lippa, S. M., Jones, R. P., Werner, J. K., Moore, C., & Kenney, K. (2026) · The Clinical Neuropsychologist · doi:10.1080/13854046.2026.2614576 · Cited by 2
“…paradoxical associations between total TBI number and time from injury may have occurred because we have relatively few confirmed NED cases in this large cohort, and this can statistically suppress or over-adjust the multivariate analyses (Belsley, 1991; O’Brien, 2007; Westreich & Greenland, 2013).”
An analytical framework for causal decision-making in international trade
Vanegas-López, J. G., Pérez-Aguirre, C. A., & López-Cadavid, D. A. (2026) · Decision Analytics Journal · doi:10.1016/j.dajour.2026.100686 · Cited by 2
Lipscomb, J., Kimmick, G. G., Wilson, J. F., Currey, A., Switchenko, J. M., Wu, X., Cress, R. D., Toumbacaris, N., Ward, K. C., & Wike, J. M. (2026) · Cancer · doi:10.1002/cncr.70267 · Cited by 2
“34 b For a patient to contribute meaningfully to an analysis of whether GC therapy influences survival outcomes, she must necessarily survive long enough to have the opportunity of being GC.”
A critical look at observational studies
Torğutalp, M., EROĞLU, D. Ş., & Taşçılar, K. (2026) · Current Opinion in Immunology · doi:10.1016/j.coi.2026.102778 · Cited by 2
Canha, D., Riveline, J., Kazanlieva, F., Aguayo, G., Bour, C., Vergès, B. L., Benhamou, P., Joubert, M., Alzaïd, F., Cosson, E., et al. (2026) · Diabetes Obesity and Metabolism · doi:10.1111/dom.70932 · Cited by 2
“As we examined specific risk factors (hypothesis-driven approach), confounders (respective base-line PAID score, age, sex and social vulnerability) were adjusted for each risk factor-outcome relationship separately, rather than combining all predictors in a single multivariable model [38, 39].”
Xu, S., Liu, H., Fan, P., Dou, H., Guo, L., Qiao, B., Li, Y., Zhou, Y., Hu, X., Guo, Y., et al. (2026) · Annals of Intensive Care · doi:10.1016/j.aicoj.2026.100132 · Cited by 2
Gasoyan, H., & Aaronson, W. E. (2020) · Journal of Healthcare Management · doi:10.1097/jhm-d-19-00207 · Cited by 2
A reanalysis: Do hog farms cause disease in North Carolina neighborhoods?
Kanankege, K. S. T., Traynor, I., & Perez, A. M. (2023) · Frontiers in Veterinary Science · doi:10.3389/fvets.2022.1052306 · Cited by 2
“Variables that result in a change of ≥10% of the ORs were considered potential confounders (32).”
BackgroundCummings, D. M., Jones, S. B., Bushnell, C., Halladay, J. R., Hart, S. L., Kinlaw, A. C., Psioda, M., Wen, F., Sissine, M. E., & Duncan, P. W. (2023) · Journal of the American Geriatrics Society · doi:10.1111/jgs.18318 · Cited by 2
“We report crude and adjusted ORs to describe associations between each independent variable and statin prescribing outcomes.(15,16) In addition, we examined these same relationships in a sub-sample that included only individuals who were not taking a statin at the time of admission to the hospital (i.”
MethodSimeunovic, G., Polega, J. R., TOOR, S. A., & Andersen, N. J. (2023) · Vaccines · doi:10.3390/vaccines11030688 · Cited by 2
“We do not report covariate effect sizes; they are likely to be biased because models were not specified to address the relationships between covariates and the outcomes of interest [24].”
BackgroundSocial determinants of self‐reported oral health among Sámi in Sweden
Yekkalam, N., Mienna, C. S., Stoor, J. P., & Sebastiån, M. S. (2023) · Community Dentistry And Oral Epidemiology · doi:10.1111/cdoe.12894 · Cited by 2
Weekly Forecasting of Yellow Fever Occurrence and Incidence via Eco‐Meteorological Dynamics
Servadio, J. L., Convertino, M., Fiecas, M. J. A., & Muñoz‐Zanzi, C. (2023) · GeoHealth · doi:10.1029/2023gh000870 · Cited by 2
“Because the aim of model selection was accurate forecasts rather than identifying unconfounded effects of individual predictors, interpreting individual parameters is subject to Table 2 fallacy (Westreich & Greenland, 2013).”
BackgroundBuilding a better model: abandon kitchen sink regression
Kuhle, S., Brown, M. M., & Stanojevic, S. (2023) · Archives of Disease in Childhood Fetal & Neonatal · doi:10.1136/archdischild-2023-326340 · Cited by 2
“20”
BackgroundMelov, S. J., Elhindi, J., White, L., McNab, J., Lee, V. W., Donnolley, K., Alahakoon, T. I., Padmanabhan, S., Cheung, N. W., & Pasupathy, D. (2023) · Nutrients · doi:10.3390/nu16010028 · Cited by 2
Trecarichi, E. M., Olivadese, V., Davoli, C., Rotundo, S., Serapide, F., Lionello, R., Tassone, B., Gamba, V. L., Fusco, P., Russo, A., et al. (2024) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1280835 · Cited by 2
“…of a response variable on the status of multiple covariates and offers a more comprehensible representation of the mechanism of the data generating process, especially when heterogeneity of effect measures across covariate levels complicates the separation of direct and indirect effects (15).”
BackgroundMethodInfluentialCorrelates of overdose among 2711 people who use drugs and live in 7 rural US sites
Fadanelli, M., “Doug”, L. M., Friedmann, P. D., Go Vivian, F., Wiley, J., Todd, K. P., William, M., Pho, M. T., David, S., Tom, S., et al. (2024) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2024.111261 · Cited by 2
The development of racial wealth gaps in early adulthood
Adames, A., & Bryer, E. (2024) · Social Science Research · doi:10.1016/j.ssresearch.2024.103010 · Cited by 2
Quintiens, B., Smets, T., Chambaere, K., den Block, L. V., Deliëns, L., & Cohen, J. (2024) · Palliative Care and Social Practice · doi:10.1177/26323524241249196 · Cited by 2
“To determine the most appropriate de-confounding strategy (and avoid the so-called ‘table 2 fallacy’), 48 we identified the possible confounders for each of the variables of interest.”
BackgroundGustavsen, E. M., Haug, E. S., Haukland, E. C., Heimdal, R., Stensland, E., Myklebust, T. Å., & Hauglann, B. (2024) · Research in Health Services & Regions · doi:10.1007/s43999-024-00044-y · Cited by 2
“Directed acyclic graphs (DAGs) was used to guide model selection for each analysis and reduce the risk of table 2 fallacy [33].”
MethodImpact of regulating political connections on employee welfare attitude: Evidence from China
Hou, X., & Zhao, J. (2024) · Journal of Asian Economics · doi:10.1016/j.asieco.2024.101760 · Cited by 2
Être étudiant avant et pendant la crise sanitaire
Facon-Barillot, Q., Romo, L., Vansimaeys, C., Chevance, A., Frajerman, A., & Morvan, Y. (2023) · La Documentation française eBooks · doi:10.3917/ldf.belgh.2023.01.0181 · Cited by 2
Differential effects of donor factors on post-transplant survival in lung transplantation
Lehr, C. J., Dalton, J. E., Dewey, E. N., Gunsalus, P. R., Rose, J., & Valapour, M. (2024) · JHLT Open · doi:10.1016/j.jhlto.2024.100122 · Cited by 2
“37 For this reason, we performed individual interaction testing to identify variables and relationships to guide further study of differential risk across age, sex, and diagnosis groups and focused on the comparison of model discrimination and calibration.”
Taylor, K. A., Carroll, M. K., Short, S. A., Celestin, B. E., Gilbertson, A., Olivier, C. B., Haddad, F., & Cauwenberghs, N. (2024) · Frontiers in Sports and Active Living · doi:10.3389/fspor.2024.1393332 · Cited by 2
Xu, J., Liu, X., & Sun, C. (2024) · Open Economies Review · doi:10.1007/s11079-024-09784-3 · Cited by 2
Svensson, M., Ekström, H., Elmståhl, S., & Rosso, A. (2024) · Archives of Gerontology and Geriatrics Plus · doi:10.1016/j.aggp.2024.100089 · Cited by 2
Feder, K. A., Li, Y., Burke, K. N., Byrne, L., Desai, I., Saloner, B. K., & Krawczyk, N. (2024) · Journal of Substance Use and Addiction Treatment · doi:10.1016/j.josat.2024.209545 · Cited by 2
Ditommaso, S., Garlasco, J., Memoli, G., Curtoni, A., Bondi, A., Ceccarelli, A., & Giacomuzzi, M. (2024) · Journal of Hospital Infection · doi:10.1016/j.jhin.2024.10.006 · Cited by 2
“However, the effect size and direction of such differences must be interpreted very cautiously, as they emerged from a model where this variable was simply conceived as a confounder [42].”
Zamanipour, B., & Keppo, I. (2024) · Energy Research & Social Science · doi:10.1016/j.erss.2024.103861 · Cited by 4
Hernandez, C. J., Sundar, K. G., Echegaray, F., Cambou, M. C., Yang, L. Z., Segura, E. R., de Melo, M. G., Santos, B. R., Varella, I. R. D. S., & Nielsen‐Saines, K. (2024) · Vaccines · doi:10.3390/vaccines12121445 · Cited by 2
“…maternal or neonatal clinical outcome of interest, with the primary exposure variables being SARS-CoV-2 infection during hospitalization and receipt of at least one dose of COVID-19 vaccine, further controlling for age, parity, gestational age, and composite score of preexisting comorbidities [21].”
Regression—A Means, Not an End
Platt, R. W. (2025) · Statistics in Medicine · doi:10.1002/sim.70000 · Cited by 2
Uncommon sex ratio at birth during the Second World War: evidence from Poland
Liczbińska, G., & Marco‐Gracia, F. J. (2025) · The History of the Family · doi:10.1080/1081602x.2025.2466487 · Cited by 2
“Hierarchical models can help mitigate the issues associated with the interpretation of results related to the fallacy shown in Table 2, though they do not entirely eliminate potential bias (Westreich & Greenland, 2013).”
Polysubstance use and mental health among young adults
Chopra, R., Sylvestre, M., Pelekanakis, A., Doré, I., Omorou, A. Y., & O’Loughlin, J. L. (2025) · Canadian Journal of Public Health · doi:10.17269/s41997-025-01035-3 · Cited by 2
“Adjustment was limited to these three covariates rather than a comprehensive model that considers all explanatory factors simultaneously in order to limit the risk of a Table 2 fallacy (Westreich & Greenland, 2013) in the interpretation of the estimated coefficients.”
Association of residential air pollution with visual impairment in adults: The UK Biobank study
Zaabaar, E., Zhang, Y., Kam, K. W., Li, Y., Zhang, X. J., Ho, M., Liu, D., Ng, M. P. H., Ip, P., Young, A. L., et al. (2025) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2025.100209 · Cited by 2
Christopoulos, K. (2025) · Geographical Analysis · doi:10.1111/gean.70010 · Cited by 2
Jeong, S. H., Kim, S. H., Park, C. W., Lee, H. S., Lee, P. H., Kim, Y. J., Sohn, Y. H., Jeong, Y., & Chung, S. J. (2025) · Clinical Nuclear Medicine · doi:10.1097/rlu.0000000000005922 · Cited by 2
Causal Inference in Public Health: A Call to Stop Causal Fishing Expeditions
Al‐kassab‐Córdova, A., & Soto-Becerra, P. (2025) · Public Health Reports · doi:10.1177/00333549251342034 · Cited by 2
“13 That is to say, the authors incorrectly assumed that each coefficient represents an independent causal effect.”
HIV Prevention Continuum Outcomes Following Implementation of a Municipal HIV Self-Testing Program
Bien-Gund, C. H., Morales, K. H., Williams, J., Hernandez, B., Ptak, B., Brady, K. A., & Gross, R. (2025) · AIDS and Behavior · doi:10.1007/s10461-025-04842-4 · Cited by 2
“We selected covariates and built separate models including the covariate of interest and confounders [21], based on our literature review [22–25].”
Michalski, S. C., Huang, Y., Srasuebkul, P., Cvejic, R. C., Arnold, S. R. C., & Trollor, J. N. (2025) · Australian & New Zealand Journal of Psychiatry · doi:10.1177/00048674251374483 · Cited by 2
“This approach allows us to estimate each variable’s total effect (direct effect + effect of mediators in the causal chain) on the outcome (Westreich and Greenland, 2013).”
Yılmaz, H., & Kocyigit, B. (2022) · PeerJ · doi:10.7717/peerj.13518 · Cited by 2
Asiimwe, S. B., Montana, L. S., Kahn, K., Tollman, S. M., Kabudula, C. W., Gómez-Olivé, F. X., Berkman, L. F., Glymour, M. M., & Bärnighausen, T. (2020) · Journal of Aging and Health · doi:10.1177/0898264320925323 · Cited by 2
“…was not the main focus of either study, so the analysis plan was not chosen to be specific to understanding the effects of HIV; prior research notes the importance of carefully selecting confounders for multivariable regression models focused on a specific exposure (Westreich & Greenland, 2013).”
MethodMajor‐Smith, D., Morgan, J., Halstead, I. N., Tohidinik, H. R., Goulding, N., Iles‐Caven, Y., Golding, J., & Northstone, K. (2022) · Wellcome Open Research · doi:10.12688/wellcomeopenres.18517.1 · Cited by 2
Can Money Buy Happiness? Income and Multidimensional Life Satisfaction in Brunei Darussalam
Slesman, L., Hoon, C. Y., Arifin, E. N., Haji-Othman, N. A., & Tan, A. (2023) · Asian Development Review · doi:10.1142/s0116110523500075 · Cited by 2
Kirui, B. K., Santosa, A., Vanfleteren, L. E. G. W., Li, H., Franzén, S., Stridsman, C., & Nyberg, F. (2023) · ERJ Open Research · doi:10.1183/23120541.00711-2022 · Cited by 2
Major‐Smith, D., Morgan, J., Halstead, I. N., Tohidinik, H. R., Goulding, N., Iles‐Caven, Y., Golding, J., & Northstone, K. (2023) · Wellcome Open Research · doi:10.12688/wellcomeopenres.18517.2 · Cited by 2
Overlooked biases from misidentifications of causal structures
Cenci, S. (2024) · The Journal of Finance and Data Science · doi:10.1016/j.jfds.2024.100127 · Cited by 2
Regression Methods for Epidemiological Analysis
Greenland, S. (2024) · Springer eBooks · doi:10.1007/978-1-4614-6625-3_17-1 · Cited by 2
Self-citationFuemmeler, B. F., Dahman, B. A., Glasgow, T. E., Barsell, D. J., Oliver, J. A., Zhang, J. J., Hoyo, C., Murphy, S. K., McClernon, F. J., & Wheeler, D. C. (2024) · Nicotine & Tobacco Research · doi:10.1093/ntr/ntae128 · Cited by 2
Volumetric Biomarkers of Visual Outcome after Surgical Repair in Lamellar Macular Holes
Lippera, M., Moussa, G., Ivanova, T., Ferrara, M., Spiess, K., Ally, N., Jasani, K., Dhawahir-Scala, F., Patton, N., & Jalil, A. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14070755 · Cited by 2
“Caution should be advised to not interpret these as main effects, but as significant moderators, to avoid a Table 2 fallacy error [29].”
BackgroundGoacher, E., Mathew, R. K., Fayaye, O., Chakrabarty, A., Feltbower, R. G., Loughrey, C., Roberts, P., & Chumas, P. (2020) · British Journal of Neurosurgery · doi:10.1080/02688697.2020.1866163 · Cited by 2
“14 These included: IDH1 status, age, sex, tumour location, tumour hemisphere, surgical management, oncological”
Kinlaw, A. C., Marx, A. H., & Farel, C. E. (2018) · Clinical Infectious Diseases · doi:10.1093/cid/ciy104 · Cited by 2
Arnold, K. F., Davies, V., de Kamps, M., Tennant, P. W. G., Mbotwa, J., & Gilthorpe, M. S. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1906.01461 · Cited by 2
(2018) · Wiley eBooks · doi:10.1002/9781118280249.refs · Cited by 2
Ongoing Lessons from the Comprehensive ESRD Care Program
Kinlaw, A. C., & Kshirsagar, A. V. (2022) · Kidney360 · doi:10.34067/kid.0008142021 · Cited by 2
“The study found that they may be less adherent to dialysis treatment than others, although these estimates lack the necessary clarity of interpretation (8) and would have been better addressed in subgroup analyses.”
BackgroundThe case for causal inference methods in resuscitation research
Kanthimathinathan, H. K., Cromie, K., & Feltbower, R. G. (2022) · Resuscitation · doi:10.1016/j.resuscitation.2022.12.004 · Cited by 2
Cheetham, N. J., Penfold, R., Giunchiglia, V., Bowyer, V., Sudre, C. H., Canas, L. S., Deng, J., Murray, B. A. K., Kerfoot, E., Antonelli, M., et al. (2023) · medRxiv · doi:10.1101/2023.03.14.23287211 · Cited by 2
Nelsen, D. R., Corbit, A. G., Chuang, A., Deitsch, J. F., Sitvarin, M. I., & Coyle, D. R. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.30.551166 · Cited by 2
“…effect esti - mates for all variables included in the model and potentially con - tributing to their misinterpretation, we only report the model coefficients for our interaction term and not for any of the other variables included to adjust for potential confounding (Westreich & Greenland, 2013 ).”
BackgroundSchulte, P. J., Goldberg, J. D., Oster, R. A., Ambrosius, W. T., Balmert, L. C., Cabral, H., Carter, R. E., Chen, Y., Desai, M., Li, D., et al. (2024) · Journal of Clinical and Translational Science · doi:10.1017/cts.2023.707 · Cited by 3
“Rather, retaining focus on the exposure of interest only will help readers avoid improper inference such as the T able 2 fallacy [75].”
BackgroundVansteelandt, S., & Steen, J. (2025) · Statistics in Medicine · doi:10.1002/sim.10312 · Cited by 2
The Relationship Between Hepatitis C Virus Rates and Office-Based Buprenorphine Access in Ohio
Brook, D., Estadt, A. T., Chettri, S. R., Schalkoff, C. A., Sibley, A. L., Lancaster, K. E., Go, V. F.-L., Miller, W. C., & Kline, D. M. (2021) · Open Forum Infectious Diseases · doi:10.1093/ofid/ofab242 · Cited by 1
“Prior studies have examined county-level vulnerability to HIV and HCV using myriad public health ecological predictors [21, 27]; however, the interpretation of the estimates of these studies represents a table 2 fallacy [28].”
Epidemiologic Methods: Seeing the Forest and the Trees
Rudolph, K. E., & Lau, B. M. (2021) · Epidemiologic Reviews · doi:10.1093/epirev/mxab010 · Cited by 1
Metadata
- Authors
- Westreich, D., & Greenland, S.
- Affiliations
- Duke University (US)
- Corresponding author
- Westreich, D.
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2013-01-30
- Volume
- 177
- Issue
- 4
- Pages
- 292-298
- ISSN
- 0002-9262 (ISSN-L)
- 1476-6256
- PMC
- PMC3626058
- OpenAlex
- W2138008655
- Cited by
- 1,276
- References
- 30
- Citations by year
- 2026: 177 · 2025: 213 · 2024: 212 · 2023: 176 · 2022: 192 · 2021: 108 · 2020: 84 · 2019: 39 · 2018: 29 · 2017: 11 · 2016: 3 · 2015: 15 · 2014: 13 · 2013: 4
- FWCI
- 10.27
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- American Journal of Epidemiology (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (AI064518)
- Duke Global Health Institute, Duke University
- University of California, Los Angeles
- National Institute of Allergy and Infectious Diseases (P30AI064518)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (R00HD063961)
- 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
- causal graphs, confounding, odds ratio, logistic regression
- MeSH terms
- HIV Seropositivity, Humans, Mathematical Computing, North Carolina, Regression Analysis, Risk Factors, Smoking, Statistics as Topic, Violence, Work, HIV Infections, Confounding Factors, Epidemiologic, Multivariate Analysis, Logistic Models, Odds Ratio, Epidemiologic Studies, Risk Assessment, Stroke
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
