The Challenge of Subgroup Analyses — Reporting without Distorting
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Subgroup analyses are an important part of the analysis of a comparative clinical trial. However, they are commonly overinterpreted14 and can lead to further research that is misguided or, worse, to suboptimal patient care.Consider a randomized, clinical trial designed to determine whether a new treatment is more effective than an established treatment and assessed with a test, based on all randomized patients, of the null hypothesis that the treatments have equal efficacy, as measured in terms of the primary end point. Then, subgroup analyses are conducted to assess whether different types of patients respond differently to the new . . .
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
“In addition, analyses of HRQoL, IBS symptoms and stool characteristics data were performed in the subgroup of those definitely constipated subjects (n = 19), as defined on the only basis of <3 stools per week; a lower significance level (P < 0.001) was applied for judging results in this subgroup, as recommended.36”
Citations
Cites
Clopidogrel and Aspirin versus Aspirin Alone for the Prevention of Atherothrombotic Events
Bhatt, D. L., Fox, K. A. A., Hacke, W., Berger, P. B., Black, H. R., Boden, W. E., Cacoub, P., Cohen, E. A., Creager, M. A., Easton, J. D., et al. (2006) · New England Journal of Medicine · doi:10.1056/nejmoa060989 · Cited by 2,837
Subgroup analysis and other (mis)uses of baseline data in clinical trials
Assmann, S. F., Pocock, S. J., Enos, L. E., & Kasten, L. E. (2000) · The Lancet · doi:10.1016/s0140-6736(00)02039-0 · Cited by 1,167
Yusuf, S. (1991) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1991.03470010097038 · Cited by 1,014
Enoxaparin versus Unfractionated Heparin with Fibrinolysis for ST-Elevation Myocardial Infarction
Antman, E. M., Morrow, D. A., McCabe, C. H., Murphy, S. A., Ruda, M., Sadowski, Z., Budaj, A., López-Sendón, J. L., Guneri, S., Jiang, F., et al. (2006) · New England Journal of Medicine · doi:10.1056/nejmoa060898 · Cited by 609
Cornell, R. G., Wolf, F. M., Bailar, J. C., & Mosteller, F. (1989) · Journal of the American Statistical Association · doi:10.2307/2289981 · Cited by 295
Yusuf, S. (1991) · JAMA · doi:10.1001/jama.266.1.93 · Cited by 129
Subgroups, treatment effects, and baseline risks: Some lessons from major cardiovascular trials
Parker, A. B., & Naylor, C. D. (2000) · American Heart Journal · doi:10.1067/mhj.2000.106610 · Cited by 61
Bailar, J. C. (1986) · Cited by 28
Cited by
Items 201–300 of 496
Gimelli, A., Pugliese, N. R., Buechel, R. R., Coceani, M. A., Clemente, A., Kaufmann, P. A., & Marzullo, P. (2020) · European Heart Journal - Cardiovascular Imaging · doi:10.1093/ehjci/jeaa298 · Cited by 24
Assessing Heterogeneity of Treatment Effects: Are Authors Misinterpreting Their Results?
Fernandez y Garcia, E., Nguyen, H., Duan, N., Gabler, N. B., & Kravitz, R. L. (2010) · Health Services Research · doi:10.1111/j.1475-6773.2009.01064.x · Cited by 23
“…of an explicit rationale); appropriate statistical analysis (through use of formal tests for interaction or heterogeneity); and balanced interpretation of the evidence (Bulpitt 1988; Yusuf et al. 1991; Altman et al. 2001; Lu et al. 2005; Rothwell 2005, 2007; Lagakos 2006; Wang et al. 2007).”
Underwood, M., Mistry, D., Lall, R., & Lamb, S. (2011) · Arthritis Care & Research · doi:10.1002/acr.20518 · Cited by 23
Risk Prediction With Procalcitonin and Clinical Rules in Community-Acquired Pneumonia
Menchine, M. D., Schriger, D. L., & Barrett, T. W. (2008) · Annals of Emergency Medicine · doi:10.1016/j.annemergmed.2008.07.010 · Cited by 23
“) 2 1 ( 3 1 ) 8 3 ( 2 4 ) 0 1 ( 1 1 15 (16) 33 (36) 14 (15) 16 (29) 25 (45) 15 (27) ) 1 2 ( 4 3 ) 8 3 ( 2 6 ) 9 1 ( 1 3 73 (17) 162 (39) 76 (18)”
NMDA Channel Antagonist MK-801 Does Not Protect against Bilirubin Neurotoxicity
Shapiro, S. M., Sombati, S., Geiger, A. S., & Rice, A. C. (2007) · Neonatology · doi:10.1159/000103743 · Cited by 23
Daptomycin compared to standard therapy for the treatment of native valve endocarditis
Kanafani, Z. A., Boucher, H. W., Fowler, V. G., Cabell, C. H., Hoen, B., Miró, J. M., Lalani, T., Vigliani, G. A., Campion, M., Corey, R. G., et al. (2010) · Enfermedades Infecciosas y Microbiología Clínica · doi:10.1016/j.eimc.2009.07.015 · Cited by 25
“aureus infection or clinical failure 8 (29) 7 (28)”
BackgroundMcFowland, E., Somanchi, S., & Neill, D. B. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3155352 · Cited by 31
Mistry, D., Stallard, N., & Underwood, M. R. (2018) · Statistics in Medicine · doi:10.1002/sim.7609 · Cited by 23
Winkelmayer, W. C., & Tonelli, M. A. (2008) · American Journal of Kidney Diseases · doi:10.1053/j.ajkd.2008.01.004 · Cited by 22
Targeting targeted agents: open issues for clinical trial design
Bria, E., Maïo, M. D., Carlini, P., Cuppone, F., Giannarelli, D., Cognetti, F., & Milella, M. (2009) · Journal of Experimental & Clinical Cancer Research · doi:10.1186/1756-9966-28-66 · Cited by 22
“On the contrary, predictive role of the marker should not be addressed with separate comparison in M+ and M- patients, because this approach, as stated before, would be associated with a high risk of false results [29].”
Yoshida, M., Nozawa, Y., Kato, D., Tabuchi, H., & Kuroishi, K. (2017) · LUTS Lower Urinary Tract Symptoms · doi:10.1111/luts.12190 · Cited by 21
Race moderates the effects of Motivational Interviewing on smoking cessation induction
Grobe, J. E., Goggin, K., Harris, K. J., Richter, K. P., Resnicow, K., & Catley, D. (2019) · Patient Education and Counseling · doi:10.1016/j.pec.2019.08.023 · Cited by 23
“Along with reduced sensitivity to detect interactions, the exploratory nature of these analyses brings up the issue of multiplicity [70], with the probability of one false alarm close to 40% and two false alarms near 10% [71].”
Backgroundvan Wyk, G. W., Hazell, P. L., Kohn, M. R., Granger, R. E., & Walton, R. J. (2012) · Journal of Attention Disorders · doi:10.1177/1087054710389989 · Cited by 20
“The advantage of this approach is that CIs provide a plausible range for the true difference between treatment groups and minimize the overinterpretation of findings that can occur when multiple analyses are conducted (Lagakos, 2006).”
BackgroundFreitas, P., Madeira, M., Raposo, L., Madeira, S., Brito, J., Brizido, C., Gama, F. F., Vale, N. C., Ranchordás, S., Magro, P. L., et al. (2018) · The American Journal of Cardiology · doi:10.1016/j.amjcard.2018.11.052 · Cited by 22
Dane, A. L., Spencer, A., Rosenkranz, G., Lipkovich, I. A., Parke, T., & on behalf of the PSI/EFSPI Working Group on Subgroup Analysis (2018) · Pharmaceutical Statistics · doi:10.1002/pst.1919 · Cited by 21
“It is acknowledged that it could equally be argued that a more stringent type I error rate should be applied as a result of the multiple testing of many subgroups.(10) It is for this reason that the simulation exercise described has explored the type I error rate, defined as the number of times a subgroup by treatment…”
BackgroundThe Rationale for Adjuvant Chemotherapy in Stage I Non-small Cell Lung Cancer
Horn, L., Sandler, A. B., Putnam, J. B., & Johnson, D. H. (2007) · Journal of Thoracic Oncology · doi:10.1097/01.jto.0000268669.64625.bb · Cited by 20
Schutt, R. K., Xie, H., Mueser, K. T., Killam, M. A., Delman, J., Eack, S. M., Mesholam‐Gately, R. I., Pratt, S. I., Sandoval, L. R., Santos, M. M., et al. (2022) · BMC Psychiatry · doi:10.1186/s12888-022-04149-x · Cited by 20
“However, rather than relying on statistical significance testing alone, we will evaluate HTE using a combination of statistical significance and clinically meaningful difference with emphasis on the magnitude of treatment effects with standard errors (clinically meaningful effect sizes) as outlined in PCORI Methodolog…”
MethodIdentifying treatment effect heterogeneity in clinical trials using subpopulations of events: STEPP
Lazar, A., Bonetti, M., Cole, B. F., Yip, W., & Gelber, R. D. (2015) · Clinical Trials · doi:10.1177/1740774515609106 · Cited by 22
“leads to chance findings since the presence of a treatment effect is separately tested in each subgroup.(1,5) For”
Song, C., Fu, R., Yang, J., Xu, H., Gao, X., Feng, L., Wang, Y., Fan, X., Ning, B., Wan, S., et al. (2019) · Nutrition Metabolism and Cardiovascular Diseases · doi:10.1016/j.numecd.2019.04.001 · Cited by 19
Lankhorst, N. E., van Middelkoop, M., Trier, Y. D. M. V., van Linschoten, R., Koes, B. W., Verhaar, J. A. N., & Bierma‐Zeinstra, S. (2015) · Journal of Orthopaedic and Sports Physical Therapy · doi:10.2519/jospt.2015.5583 · Cited by 23
MacFarlane, L. A., Yang, H. Y., Collins, J. E., Guermazi, A., Jones, M. H., Spindler, K. P., Winter, A. R., Losina, E., Katz, J. N., and the MeTeOR Investigator Group, et al. (2019) · The American Journal of Sports Medicine · doi:10.1177/0363546518819444 · Cited by 19
Lee, J., & Oh, M. (2019) · Addictive Behaviors · doi:10.1016/j.addbeh.2019.01.038 · Cited by 19
Fondaparinux versus Enoxaparin in Acute Coronary Syndromes
Majure, D. T., & Aberegg, S. K. (2006) · New England Journal of Medicine · doi:10.1056/nejmc061206 · Cited by 19
Venekamp, R. P., Rovers, M. M., Hoes, A. W., & Knol, M. J. (2014) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2013.11.003 · Cited by 18
Identifying Heterogeneous Effect Using Latent Supervised Clustering With Adaptive Fusion
Chen, J., Tran-Dinh, Q., Kosorok, M. R., & Liu, Y. (2020) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2020.1763808 · Cited by 18
“In practice, it takes tremendous efforts to search for the targeted subpopulation of certain interventions (Brookes et al. 2004; Lagakos 2006).”
BackgroundCombining lymphovascular invasion with reactive stromal grade predicts prostate cancer mortality
Sæter, T., Vlatkovic, L., Waaler, G., Servoll, E., Nesland, J. M., Axcrona, K., & Axcrona, U. (2016) · The Prostate · doi:10.1002/pros.23192 · Cited by 20
“Finally, subgroup and interaction analyses are susceptible to several pitfalls such as false positives results and inadequate power [27].”
BackgroundThomas, Z., & Fraser, G. L. (2007) · Annals of Pharmacotherapy · doi:10.1345/aph.1k082 · Cited by 20
Whitlock, E. P., Eder, M. L., Thompson, J. H., Jonas, D. E., Evans, C. V., Guirguis‐Blake, J., & Lin, J. S. (2017) · Systematic Reviews · doi:10.1186/s13643-017-0437-3 · Cited by 19
“Because the probability of a false positive result is high when a large number of subgroup analyses are conducted, studies can correct for the inflated false positive rate by adjusting the significance threshold for their interaction tests [55].”
BackgroundInfluentialClinical trials: design, endpoints and interpretation of outcomes
Othus, M. K. D., Zhang, M.-J., & Gale, R. P. (2022) · Bone Marrow Transplantation · doi:10.1038/s41409-021-01542-0 · Cited by 20
Overcoming Challenges in Multisite Trials
Smith, L. H., Tan, A., Stephens, J. D., Hibler, D., & Duffy, S. A. (2019) · Nursing Research · doi:10.1097/nnr.0000000000000324 · Cited by 19
Prasinezumab slows motor progression in Parkinsons disease: beyond the clinical data
Xiao, B., & Tan, E. (2025) · npj Parkinson s Disease · doi:10.1038/s41531-025-00886-4 · Cited by 24
Subgroup analysis for the risk of cardiovascular disease with calcium supplements
Radford, L. T., Bolland, M. J., Gamble, G. D., Grey, A. B., & Reid, I. R. (2013) · BoneKEy Reports · doi:10.1038/bonekey.2013.27 · Cited by 17
Vermeij, J., Westendorp, W. F., Roos, Y. B. W. E. M., Brouwer, M. C., van de Beek, D., Nederkoorn, P. J., & for the PASS Investigators (2016) · Cerebrovascular Diseases · doi:10.1159/000446160 · Cited by 20
Hemilä, H. (2016) · British Journal Of Nutrition · doi:10.1017/s0007114516003408 · Cited by 17
“Feinstein wanted to ‘rescue the scientific importance of valid pathophysiologic subgroups from being forgotten or destroyed by excessive vehemence in suggestions that all subgroups are evil’((28)) and Lagakos commented that ‘avoiding any presentation of subgroup analysis because of their history of being over-interpre…”
BackgroundSmoking is Not a Good Prognostic Factor following First-Ever Acute Ischemic Stroke
Lee, J.-H., Lee, J. Y., Ahn, S. H., Jang, M. U., Oh, M. S., Kim, C.-H., Yu, K., & Lee, B. (2015) · Journal of Stroke · doi:10.5853/jos.2015.17.2.177 · Cited by 18
“In our subgroup analysis, smokers with thrombolytic therapy tended to have a poorer outcome than nonsmokers; however, the false positive rates associated with the application of multiple statistical tests may be high; the probability of one or more false positive findings when 9 subgroup tests are performed is about 4…”
Annotated chromosome maps for renal disease
McKnight, A. J., O'Donoghue, D. J., & Maxwell, A. P. (2008) · Human Mutation · doi:10.1002/humu.20885 · Cited by 17
“Typical linkage studies have limited statistical power to detect susceptibility alleles [Burgner et al., 2006], particularly when linkage is reported from subgroup analysis, which may inflate the false positive rate [Lagakos, 2006].”
BackgroundResultWeisler, R., Childress, A., Adler, L., Kollins, S., Goodman, D., Hamdani, & Dirks, B. (2013) · Neuropsychiatric Disease and Treatment · doi:10.2147/ndt.s47087 · Cited by 16
“…above, the rationale for not pursuing comparative statistical analysis involved a consideration of several factors, including: prior commentary 40,41 recommending against comparative statistical analysis of post hoc subgroup data sets; the small number of participants in many of the subgroups…”
Iterative Causal Forest: A Novel Algorithm for Subgroup Identification
Wang, T., Keil, A. P., Kim, S., Wyss, R., Htoo, P. T., Funk, M. J., Buse, J. B., Kosorok, M. R., & Stürmer, T. (2023) · American Journal of Epidemiology · doi:10.1093/aje/kwad219 · Cited by 17
Fortune, D. G., Rogan, C., & Richards, H. L. (2015) · British Journal of Health Psychology · doi:10.1111/bjhp.12159 · Cited by 17
Mroz, T. E., Norvell, D. C., Ecker, E. D., Gruenberg, M. F., Dailey, A. T., & Brodke, D. S. (2011) · Spine · doi:10.1097/brs.0b013e31822ef68c · Cited by 19
Adjuvant Chemotherapy for Non-small Cell Lung Cancer
Bria, E., Cuppone, F., Cecere, F. L., Milella, M., Nisticò, C., Cognetti, F., & Terzoli, E. (2007) · Journal of Thoracic Oncology · doi:10.1097/01.jto.0000268633.87529.75 · Cited by 16
“24,32 It is certain that the paradigm in the treatment of early-stage NSCLC has shifted in the past 3 years; the positive results of RCTs accruing more than 7000 patients and the meta-analyses performed offered promising results in favor of adjuvant chemotherapy.”
LUX-Lung: determining the best EGFR inhibitor in NSCLC?
Rossi, A., & Maïo, M. D. (2015) · The Lancet Oncology · doi:10.1016/s1470-2045(14)71196-9 · Cited by 16
Chemoprevention of Second Cancers
Mayne, S. T., & Cartmel, B. (2006) · Cancer Epidemiology Biomarkers & Prevention · doi:10.1158/1055-9965.epi-06-0415 · Cited by 16
“Clinical trialists appropriately caution against overinterpretation of subgroup effects within trials (19).”
Efficacy and safety of caspofungin in obese patients
Ryan, D., Lupinacci, R. J., & Kartsonis, N. A. (2011) · Medical Mycology · doi:10.3109/13693786.2011.571293 · Cited by 18
Approaches to treatment effect heterogeneity in the presence of confounding
Anoke, S. C., Normand, S. T., & Zigler, C. M. (2019) · Statistics in Medicine · doi:10.1002/sim.8143 · Cited by 22
“For clarity, the x-axes of the forest plots have been omitted, but there are vertical dashed lines denoting the true ATEs (1, 2, 5, 6, 9, 10).”
BackgroundInfluentialMorphew, T. L., Shin, H., Marchese, S., Pires-Barracosa, N., & Galant, S. P. (2019) · Annals of Allergy Asthma & Immunology · doi:10.1016/j.anai.2019.05.008 · Cited by 17
Martinez, L. S. S., Lundgren, L. M., Walter, A. W., Sousa, J., Tahoun, N., Steketee, G. S., Hahm, H. C., Mueser, K. T., Krull, I., Lien, D., et al. (2019) · Journal of the Society for Social Work and Research · doi:10.1086/704070 · Cited by 16
“This is not surprising given the limits of subgroup analyses in RCTs, including their impact on study power (Lagakos, 2006; Wang, Lagakos, Ware, Hunter, & Drazen, 2007).”
BackgroundBiliverdin-induced brainstem auditory evoked potential abnormalities in the jaundiced Gunn rat
Rice, A. C., & Shapiro, S. M. (2006) · Brain Research · doi:10.1016/j.brainres.2006.06.005 · Cited by 16
Rayman, N., Lam, K. H., van der Holt, B., Koss, C., Veldhuizen, D., Budel, L. M., Mulder, A. H., Verdonck, L. F., Delwel, R., de Jong, D., et al. (2011) · Clinical Lymphoma Myeloma & Leukemia · doi:10.3816/clml.2011.n.003 · Cited by 15
The Clinical Significance of Statistical Significance
Kane, R. C. (2008) · The Oncologist · doi:10.1634/theoncologist.2008-0186 · Cited by 15
A statistical primer on subgroup analyses
Milojevic, M., Nikolić, A., Jüni, P., & Head, S. J. (2020) · Interactive Cardiovascular and Thoracic Surgery · doi:10.1093/icvts/ivaa042 · Cited by 17
Statistical power of multiplicity adjustment strategies for correlated binary endpoints
Leon, A. C., Heo, M., Teres, J. J., & Morikawa, T. (2007) · Statistics in Medicine · doi:10.1002/sim.2795 · Cited by 16
“Instead one multiplicity adjustment procedure should be identified in the study protocol before the data are analysed, whether for multiple-dependent variables or multiple subgroups [23].”
BackgroundChoma, T. J., Schuster, J. M., Norvell, D. C., Dettori, J. R., & Chutkan, N. B. (2011) · Spine · doi:10.1097/brs.0b013e31822ef89e · Cited by 17
The Green Heart Project: objectives, design, and methods
Bhatnagar, A., Keith, R. J., Yeager, R. A., Riggs, D. W., Sears, C. G., Bucknum, B., Smith, T., Fleischer, D., Chandler, C., Walker, K. L., et al. (2024) · American Journal of Epidemiology · doi:10.1093/aje/kwae458 · Cited by 16
Psychiatric Aspects of Induced Abortion
Stotland, N. L. (2011) · The Journal of Nervous and Mental Disease · doi:10.1097/nmd.0b013e318225f135 · Cited by 14
Shirani, A., Zhao, Y., Karim, M. E., Petkau, J., Gustafson, P., Evans, C. D., Kingwell, E., van der Kop, M. L., Oger, J., & Tremlett, H. L. (2013) · European Journal of Neurology · doi:10.1111/ene.12324 · Cited by 14
Kovalchik, S. A. (2012) · Biostatistics · doi:10.1093/biostatistics/kxs035 · Cited by 16
“In clinical trial research, the aims to personalize treatment and avoid spurious findings from subgroup analyses have often seemed irreconcilable (Lagakos, 2006).”
BackgroundSumner, W., Amini, A., Hankinson, T. C., Foreman, N. K., Gaspar, L. E., Kavanagh, B. D., Karam, S. D., Rusthoven, C. G., & Liu, A. K. (2017) · Reports of Practical Oncology & Radiotherapy · doi:10.1016/j.rpor.2017.10.001 · Cited by 14
Subgroup identification via homogeneity pursuit for dense longitudinal/spatial data
Li, J., Yue, M., & Zhang, W. (2019) · Statistics in Medicine · doi:10.1002/sim.8192 · Cited by 14
Evolving Perspectives on Clopidogrel in the Treatment of Ischemic Stroke
Gorelick, P. B., Sechenova, O., & Hennekens, C. H. (2006) · Journal of Cardiovascular Pharmacology and Therapeutics · doi:10.1177/1074248406296862 · Cited by 15
“For all of these reasons, subgroup analyses should be viewed as hypothesis formulating, not hypothesis testing.(7,9) Regarding other combination therapies, in the second European Stroke Prevention Study (ESPS-2), 6602 patients with a history of recent stroke or TIA were randomized to placebo, aspirin monotherapy, exte…”
BackgroundHextrum, S., & Bennett, S. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00011 · Cited by 15
“005 if 10 subgroups were analyzed (11).”
Fluoxetine After Weight Restoration in Anorexia Nervosa: A Randomized Controlled Trial
Walsh, B. T., Kaplan, A. S., Attia, E., Olmsted, M., Parides, M., Carter, J. C., Pike, K. M., Devlin, M. J., Woodside, B., Roberto, C. A., et al. (2006) · JAMA · doi:10.1001/jama.295.22.2605 · Cited by 13
“Kaye, MD, Western Psychiatric Institute and Clinic, University of Pittsburgh School of Medicine, and the restriction of the analysis to a subgroup may have inflated the possibility of a false-positive result.(27) The current study has implications for both clinical practice and research.”
BackgroundCai, J., Xie, D., Kong, F., Zhai, Z., Zhu, Z., Zhao, Y., Xu, Y., & Sun, T. (2024) · Journal of Alzheimer s Disease · doi:10.3233/jad-231249 · Cited by 13
“…analysis refers to the process of dividing the study population into different subgroups according to some characteristic of the study population (e.g., modeling method), and then separately estimating the effect values for the different groups and conducting comparisons between the subgroups [28].”
Interaction analysis of subgroup effects in randomized trials: the essential methodological points
Fingerhut, A. L., Uranues, S., Dziri, C., Ma, J., Vernerey, D., Kurihara, H., & Stiegler, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-62896-1 · Cited by 15
Active Clinical Trials for Personalized Medicine
Minsker, S., Zhao, Y., & Cheng, G. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1066682 · Cited by 13
“Consequently, post-mining data from RCTs is not ideal for finding optimal treatment strategies (Cui et al., 2002; Lagakos, 2006).”
MethodReeve, H. W. J., Cannings, T. I., & Samworth, R. J. (2023) · The Annals of Statistics · doi:10.1214/23-aos2328 · Cited by 22
Novel Anti-arrhythmic Medications in the Treatment of Atrial Fibrillation
Saklani, P., & Skanes, A. C. (2012) · Current Cardiology Reviews · doi:10.2174/157340312803760785 · Cited by 13
Pre-referral rectal artesunate in severe malaria: flawed trial
Hirji, K. F., & Premji, Z. G. (2011) · Trials · doi:10.1186/1745-6215-12-188 · Cited by 13
“The medical literature abounds with warnings about the pitfalls of such analyses [42-51].”
BackgroundAbrahamson, P. E., Tworoger, S. S., Aiello, E. J., Bernstein, L., Ulrich, C. M., Gilliland, F. D., Stanczyk, F. Z., Baumgartner, R., Baumgartner, K. B., Sorensen, B. E., et al. (2006) · Breast Cancer Research and Treatment · doi:10.1007/s10549-006-9426-2 · Cited by 13
“However, our subgroup findings for CYP17 and SHBG may also be due to chance given our small numbers and making multiple statistical comparisons [41].”
Clustered federated learning based on nonconvex pairwise fusion
Yu, X., Liu, Z., Wang, W., & Sun, Y. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120956 · Cited by 12
Flexible shrinkage estimation of subgroup effects through Dirichlet process priors
Gamalo, M., Tiwari, R. C., & LaVange, L. M. (2016) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543406.2016.1226327 · Cited by 13
“© 2016 Taylor & Francis Lagakos, 2006) have been published recommending that appropriate emphasis should always be placed on the primary outcome of the study and to plan investigations for expected heterogeneity.”
BackgroundUpdate on the Cardiovascular Risks of Hormone Replacement Therapy
Lowe, G. D. O. (2006) · Women s Health · doi:10.2217/17455057.3.1.87 · Cited by 13
Design and Conduct of Clinical Trials
Antman, E. M. (2012) · Elsevier eBooks · doi:10.1016/b978-1-4377-0398-6.00006-8 · Cited by 12
Treatment of Hypertension in the Elderly
Δούμα, Σ., Petidis, K., & Zamboulis, C. (2008) · New England Journal of Medicine · doi:10.1056/nejmc081224 · Cited by 14
Ishani, A., Hau, C., Cushman, W. C., Leatherman, S. M., Lew, R., Glassman, P. A., Taylor, A. A., & Ferguson, R. E. (2024) · JAMA Network Open · doi:10.1001/jamanetworkopen.2024.11081 · Cited by 11
Yu, H., Zhong, H., Liu, Y., & Zhang, G. (2024) · Clinical Kidney Journal · doi:10.1093/ckj/sfae383 · Cited by 11
“We first conducted heterogeneity tests for each indicator, based on the methodologies of the included articles and intervention studies [22 ].”
Optimal Treatment Assignment to Maximize Expected Outcome with Multiple Treatments
Lou, Z., Shao, J., & Yu, M. (2017) · Biometrics · doi:10.1111/biom.12811 · Cited by 11
“This topic is closely related with subgroup identification since patients benefited from the optimal treatment assignment can be formed as a subgroup, although the controversy and challenge of subgroup identification have been well documented (Lagakos, 2006; Ruberg et al., 2010).”
BackgroundStudying treatment-effect heterogeneity in precision medicine through induced subgroups
Sies, A., Demyttenaere, K., & Mechelen, I. V. (2019) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543406.2019.1579220 · Cited by 15
“…subjecting the result to a (large) number of formal tests causing problems of multiple testing (see, e.g., Brookes et al. (2004); Sleight (2000); Lagakos (2006)), (c) performing underpowered studies (e.g., detecting interactions of the same size as a main effect with the same power requires a…”
BackgroundResearch and scholarly methods: Subgroup analysis
Ding, Q., Wan, S., & Dowling, T. C. (2022) · JACCP JOURNAL OF THE AMERICAN COLLEGE OF CLINICAL PHARMACY · doi:10.1002/jac5.1611 · Cited by 11
“005 as the significance level.(3,27,29) Selective reporting of post hoc subgroup observations or selective reporting of significant analyses regardless of the overall nonsignificant results is a data-generating method, instead of hypothesis testing.”
BackgroundClephas, P. R. D., Zwartkruis, V. W., Malgie, J., van Gent, M. W. F., Rocca, H. B., Szymanski, M. K., van Halm, V. P., Handoko, M. L., Kok, W. E. M., Asselbergs, F. W., et al. (2024) · European Heart Journal · doi:10.1093/eurheartj/ehae323 · Cited by 13
“26 Conversely, others argue that utilizing interaction tests already addresses significant concerns regarding multiple comparisons, 27 and that adjusting for multiple testing may further reduce statistical power.”
BackgroundLokhorst, H. M., van der Holt, B., Cornelissen, J. J., Kersten, M. J., van Oers, M. H. J., Raymakers, R. A. P., Minnema, M. C., Zweegman, S., Bos, G. M. J., Schaap, N. P., et al. (2015) · Haematologica · doi:10.3324/haematol.2015.128728 · Cited by 12
“> 3 mg/l) and the presence or absence of deletion 13 (determined by FISH and/or by karyotyping).(14) KaplanMeier curves were generated to illustrate differences between subgroups.”
Pharmacology and Statistics: Recommendations to Strengthen a Productive Partnership
Spector, R., & Vesell, E. S. (2006) · Pharmacology · doi:10.1159/000095961 · Cited by 13
“Another thorny problem involves drug effect on subgroups in trials. In general, a primary hypothesis is posed and perhaps one or two secondary hypotheses. The primary hypothesis usually deals with the mean or median, or with a life table analysis, but reveals nothing about subgroups. In our view, if the primary hypoth…”
BackgroundInfluentialBig risks in small groups: The difference between epidemiology and counselling
Friedman, J. M. (2009) · Birth Defects Research Part A Clinical and Molecular Teratology · doi:10.1002/bdra.20606 · Cited by 13
for the OlmeSartan Calcium Antagonists Randomized (OSCAR) Study Group, Matsui, K., Kim‐Mitsuyama, S., Ogawa, H., Jinnouchi, T., Jinnouchi, H., & Arakawa, K. (2014) · Hypertension Research · doi:10.1038/hr.2014.23 · Cited by 11
Statistical Analysis of Comet Assay Data
Lovell, D. P. (2009) · Royal Society of Chemistry eBooks · doi:10.1039/9781847559746-00424 · Cited by 11
When to start and stop caffeine and why respiratory status matters
Davis, P. G. (2020) · Seminars in Fetal and Neonatal Medicine · doi:10.1016/j.siny.2020.101175 · Cited by 11
Moderators of gene-outcome associations following traumatic brain injury
Carmichael, J. J., Hicks, A. J., Spitz, G., Gould, K. R., & Ponsford, J. L. (2021) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2021.08.015 · Cited by 11
Mahaffey, K. W., & Harrington, R. A. (2007) · JAMA · doi:10.1001/jama.297.6.636 · Cited by 11
Nordbeck, P., Göker-Alpan, Ö., Bernat, J. A., Germain, D. P., Giraldo, P., Jovanović, A., Kimonis, V. E., Nicholls, K., Greenberg, C. R., Schiffmann, R., et al. (2026) · Nature Communications · doi:10.1038/s41467-025-68256-5 · Cited by 10
“The limitations of post-hoc subgroup analyses are acknowledged 31,32 .”
Does the Life Skills Training program reduce use of marijuana?
Gorman, D. M. (2011) · Addiction Research & Theory · doi:10.3109/16066359.2011.557164 · Cited by 10
“…the application of multiple statistical tests to a dataset and this increases the chance of finding differences between study conditions through chance alone, that is false positive results or Type I error (Lagakos, 2006; Lord, Gebski, & Keech, 2004; Wang, Lagakos, Ware, Hunter, & Drazen, 2007).”
BackgroundThe nuts and bolts of hypothesis testing
Pugh, S. L., & Molinaro, A. M. (2015) · Neuro-Oncology Practice · doi:10.1093/nop/npv052 · Cited by 12
“There are many other methods to control for inflated type I errors, some depend on having correlated data and are not as conservative as the Bonferroni approach.(6)”
MethodHemilä, H., Chalker, E., & Tukiainen, J. (2022) · Frontiers in Pharmacology · doi:10.3389/fphar.2022.817522 · Cited by 11
“Nevertheless, Lagakos commented that “avoiding any presentation of subgroup analysis because of their history of being over-interpreted is a steep price to pay for a problem that can be remedied by more responsible analysis and reporting” (Lagakos, 2006).”
BackgroundResearch Note: Treatment effect moderators
Hancock, M. J., & Kent, P. M. (2022) · Journal of physiotherapy · doi:10.1016/j.jphys.2022.08.006 · Cited by 11
Sato, Y., Yoshihisa, A., Ide, T., Tohyama, T., Enzan, N., Matsushima, S., Tsutsui, H., & Takeishi, Y. (2023) · Circulation Journal · doi:10.1253/circj.cj-22-0774 · Cited by 10
Lin, J., Bunn, V., & Liu, R. (2019) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2018.1560360 · Cited by 10
Barker, D., Scott‐Sheldon, L. A. J., Stone, D. I. G., & Brown, L. K. (2019) · Archives of Sexual Behavior · doi:10.1007/s10508-019-01526-8 · Cited by 10
“These differences are magnified when used to identify treatment modifiers, which complicates the already challenging process of individualizing intervention approaches (Lagakos, 2006).”
BackgroundAdjuvant chemotherapy for local relapse breast cancer
Pivot, X. B. (2014) · The Lancet Oncology · doi:10.1016/s1470-2045(13)70610-7 · Cited by 10
DiNubile, M. J., Strohmaier, K. M., Lupinacci, R. J., Meibohm, A. R., Sable, C. A., & Kartsonis, N. A. (2008) · European Journal of Clinical Microbiology & Infectious Diseases · doi:10.1007/s10096-008-0486-6 · Cited by 10
Friedman, L. M., Furberg, C. D., & DeMets, D. L. (2010) · Springer eBooks · doi:10.1007/978-1-4419-1586-3_17 · Cited by 10
Biostatistiques médicales avec GMRC Shiny Stats – un outil de formation par la pratique
Fabacher, T., Schaeffer, M., Tuzin, N., Séverac, F., Lefebvre, F., Mielcarek, M., Sauleau, E., Meyer, N., & Godet, J. (2020) · Annales Pharmaceutiques Françaises · doi:10.1016/j.pharma.2020.06.001 · Cited by 10
Metadata
- Authors
- Lagakos, S. W.
- Affiliations
- Harvard University (US)
- Corresponding author
- Lagakos, Stephen W.
- Venue
- New England Journal of Medicine
- Publisher
- Massachusetts Medical Society
- Published
- 2006-04-20
- Volume
- 354
- Issue
- 16
- Pages
- 1667-1669
- ISSN
- 0028-4793 (ISSN-L)
- 1533-4406
- OpenAlex
- W2085477178
- Semantic Scholar
- d03b954bb3525ed19f989e831c39645293c3c984
- Cited by
- 504
- References
- 7
- Citations by year
- 2026: 8 · 2025: 11 · 2024: 23 · 2023: 13 · 2022: 14 · 2021: 13 · 2020: 21 · 2019: 34 · 2018: 21 · 2017: 21 · 2016: 23 · 2015: 29 · 2014: 21 · 2013: 26 · 2012: 29
- FWCI
- 40.60
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- New England Journal of Medicine (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Keywords
- subgroup analysis, subgroup heterogeneity, overinterpretation, reporting bias, treatment effect heterogeneity, randomized controlled trials, primary endpoint
- MeSH terms
- Data Interpretation, Statistical, False Positive Reactions, Probability, Statistics as Topic, Randomized Controlled Trials as Topic
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.