The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Randomization, Statistics, and Causal Inference
Abstract
This paper reviews the role of statistics in causal inference. Special attention is given to the need for randomization to justify causal inferences from conventional statistics, and the need for random sampling to justify descriptive inferences. In most epidemiologic studies, randomization and random sampling play little or no role in the assembly of study cohorts. I therefore conclude that probabilistic interpretations of conventional statistics are rarely justified, and that such interpretations may encourage misinterpretation of nonrandomized studies. Possible remedies for this problem include deemphasizing inferential statistics in favor of data descriptors, and adopting statistical techniques based on more realistic probability models than those in common use.
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?
Confidence intervals do not take into account other uncertainties that arise from a study's design, implementation, and methods of measurement.
“The latter do not take into account other uncertainties that arise from a study's design, implementation, and methods of measurement [ 209 ].”
From Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): Explanation and Elaboration (2007) · cites this paper as [209]
Citations
Cites
Modeling and variable selection in epidemiologic analysis
Greenland, S. (1989) · American Journal of Public Health · doi:10.2105/ajph.79.3.340 · Cited by 2,208
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Moher, D., Hopewell, S., Schulz, K. F., Montori, V., Gotzsche, P. C., Devereaux, P. J., Elbourne, D., Egger, M., & Altman, D. G. (2010) · BMJ · doi:10.1136/bmj.c869 · Cited by 8,883
Vandenbroucke, J. P., von Elm, E., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S. J., Poole, C., Schlesselman, J. J., Egger, M., & Initiative, F. T. S. (2007) · PLoS Medicine · doi:10.1371/journal.pmed.0040297 · Cited by 8,613
“The latter do not take into account other uncertainties that arise from a study’s design, implementation, and methods of measurement [209].”
Sensitivity analysis in observational research: Introducing the E-value
VanderWeele, T. J., & Ding, P. (2017) · Annals of Internal Medicine · doi:10.7326/m16-2607 · Cited by 6,350
“, that some third factor related to both the treatment and the outcome might explain their association, with no true causal effect(12-22).”
BackgroundSPIRIT 2013 explanation and elaboration: guidance for protocols of clinical trials
Chan, A.-W., Tetzlaff, J. M., Gotzsche, P. C., Altman, D. G., Mann, H., Berlin, J. A., Dickersin, K., Hrobjartsson, A., Schulz, K. F., Parulekar, W. R., et al. (2013) · BMJ · doi:10.1136/bmj.e7586 · Cited by 6,251
The Revised CONSORT Statement for Reporting Randomized Trials: Explanation and Elaboration
Altman, D. G., Schulz, K. F., Moher, D., Egger, M., Davidoff, F., Elbourne, D., Gøtzsche, P. C., Lang, T., & for the CONSORT Group (2001) · Annals of Internal Medicine · doi:10.7326/0003-4819-134-8-200104170-00012 · Cited by 3,835
Vandenbroucke, J. P., Elm, E. V., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S. J., Poole, C., Schlesselman, J. J., Egger, M., & initiative, F. T. S. (2007) · Annals of Internal Medicine · doi:10.7326/0003-4819-147-8-200710160-00010-w1 · Cited by 3,543
Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations
Greenland, S., Senn, S. J., Rothman, K. J., Carlin, J. B., Poole, C., Goodman, S. N., & Altman, D. G. (2016) · European Journal of Epidemiology · doi:10.1007/s10654-016-0149-3 · Cited by 3,200
Self-citationVandenbroucke, J. P., von Elm, E., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S. J., Poole, C., Schlesselman, J. J., & Egger, M. (2014) · International Journal of Surgery · doi:10.1016/j.ijsu.2014.07.014 · Cited by 2,969
“]. Authors should address the real range of uncertainty in estimates, which is larger than the statistical uncertainty reflected in confidence intervals. The latter do not take into account other uncertainties that arise from a study's design, implementation, and methods of measurement [”
Vandenbroucke, J. P., von Elm, E., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S. J., Poole, C., Schlesselman, J. J., & Egger, M. (2007) · Epidemiology · doi:10.1097/ede.0b013e3181577511 · Cited by 2,779
Moher, D., Hopewell, S., Schulz, K. F., Montori, V., Gøtzsche, P. C., Devereaux, P. J., Elbourne, D., Egger, M., & Altman, D. G. (2012) · International Journal of Surgery · doi:10.1016/j.ijsu.2011.10.001 · Cited by 2,345
“Second, random assignment permits the use of probability theory to express the likelihood that any difference in outcome between intervention groups merely reflects chance [26].”
Moher, D., Hopewell, S., Schulz, K. F., Montori, V., Gøtzsche, P. C., Devereaux, P. J., Elbourne, D., Egger, M., & Altman, D. G. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2010.03.004 · Cited by 1,858
Understanding and misunderstanding randomized controlled trials
Deaton, A., & Cartwright, N. (2018) · Social Science & Medicine · doi:10.1016/j.socscimed.2017.12.005 · Cited by 1,841
“(An instructive example of perfect random confounding is constructed by Greenland (1990).)”
InfluentialTunis (2003) · doi:10.1001/jama.290.12.1624 · Cited by 1,724
Confounding and Collapsibility in Causal Inference
Greenland, S., Pearl, J., & Robins, J. M. (1999) · Statistical Science · doi:10.1214/ss/1009211805 · Cited by 933
Self-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-citationThe (mis)estimation of neighborhood effects: causal inference for a practicable social epidemiology
Oakes, J. M. (2003) · Social Science & Medicine · doi:10.1016/j.socscimed.2003.08.004 · Cited by 767
“For contemporary insights and cautions about purely ecological studies, see Morgenstern (1995) and Greenland (2001). for scientific understanding and sound policy recommendations for improving the public’s health.”
BackgroundInfluentialA dirty dozen: twelve p-value misconceptions.
Goodman, S. (2008) · Seminars in hematology (Print) · doi:10.1053/j.seminhematol.2008.04.003 · Cited by 694
Basic methods for sensitivity analysis of biases.
Greenland, S. (1996) · International Journal of Epidemiology · doi:10.1093/ije/25.6.1107 · Cited by 605
Self-citationMeat consumption and risk of colorectal cancer.
Chao, A., Thun, M., Connell, C., McCullough, M., Jacobs, E., Flanders, W., Rodríguez, C., Sinha, R., & Calle, E. (2005) · Journal of the American Medical Association (JAMA) · doi:10.1001/jama.293.2.172 · Cited by 569
Generalizing evidence from randomized clinical trials to target populations: The ACTG 320 trial.
Cole, S., & Stuart, E. (2010) · American Journal of Epidemiology · doi:10.1093/aje/kwq084 · Cited by 535
Vandenbroucke, J. P., von Elm, E. B., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S., Poole, C., Schlesselman, J. J., & Egger, M. (2009) · Gaceta Sanitaria · doi:10.1016/j.gaceta.2008.12.001 · Cited by 215
Principles of multilevel modelling.
Greenland, S. (2000) · International Journal of Epidemiology · doi:10.1093/ije/29.1.158 · Cited by 500
Self-citationMaldonado, G., & Greenland, S. (2002) · International Journal of Epidemiology · doi:10.1093/intjepid/31.2.422 · Cited by 396
Self-citationKrithikadatta, J., Datta, M., & Gopikrishna, V. (2014) · Journal of Conservative Dentistry · doi:10.4103/0972-0707.136338 · Cited by 472
Confounding in Health Research
Greenland, S., & Morgenstern, H. (2001) · Annual Review of Public Health · doi:10.1146/annurev.publhealth.22.1.189 · Cited by 390
“As discussed below, confounding is also possible in randomized experiments because of systematic elements in treatment allocation, administration, and compliance and because of random differences between comparison groups (22, 30, 36, 38, 87).”
BackgroundSelf-citationDemonstration of deductive meta-analysis: ethanol intake and risk of myocardial infarction
Maclure, M. (1993) · Epidemiologic Reviews · doi:10.1093/oxfordjournals.epirev.a036124 · Cited by 397
Bayesian perspectives for epidemiological research: I. Foundations and basic methods
Greenland, S. (2006) · International Journal of Epidemiology · doi:10.1093/ije/dyi312 · Cited by 383
Self-citationFish Consumption and Risk of Stroke in Men
He, K. (2002) · JAMA · doi:10.1001/jama.288.24.3130 · Cited by 340
Low P-Values or Narrow Confidence Intervals: Which Are More Durable?
Poole, C. (2001) · Epidemiology · doi:10.1097/00001648-200105000-00005 · Cited by 363
Ecologic versus individual-level sources of bias in ecologic estimates of contextual health effects
Greenland, S. (2001) · International Journal of Epidemiology · doi:10.1093/ije/30.6.1343 · Cited by 304
Self-citationA method to automate probabilistic sensitivity analyses of misclassified binary variables
Fox, M. P., Lash, T. L., & Greenland, S. (2005) · International Journal of Epidemiology · doi:10.1093/ije/dyi184 · Cited by 286
Self-citationStatistical Rituals: The Replication Delusion and How We Got There
Gigerenzer, G. (2018) · Advances in Methods and Practices in Psychological Science · doi:10.1177/2515245918771329 · Cited by 263
“…descriptive statistics and exploratory data analysis (Breiman, 2001; L. V. Jones & Tukey, 2000) are good candidates for the scores of situations in which no random samples have been drawn from defined populations and the assumptions of the statistical models are not in place (Greenland, 1990).”
BackgroundRisk Factors, Confounding, and the Illusion of Statistical Control
Christenfeld, N. J. S., Sloan, R. P., Carroll, D., & Greenland, S. (2004) · Psychosomatic Medicine · doi:10.1097/01.psy.0000140008.70959.41 · Cited by 260
Self-citationCan Policies Stall the Fertility Fall? A Systematic Review of the (Quasi‐) Experimental Literature
Bergsvik, J., Fauske, A., & Hart, R. K. (2021) · Population and Development Review · doi:10.1111/padr.12431 · Cited by 259
Beyond randomized controlled trials: A critical comparison of trials with nonrandomized studies
Sørensen, H., Lash, T., & Rothman, K. (2006) · Hepatology · doi:10.1002/hep.21404 · Cited by 257
Nitsch, D., Molokhia, M., Smeeth, L. L., Stavola, B. L. D., Whittaker, J. C., & Leon, D. A. (2006) · American Journal of Epidemiology · doi:10.1093/aje/kwj062 · Cited by 228
Stürmer, T., Schneeweiß, S., Avorn, J., & Glynn, R. J. (2005) · American Journal of Epidemiology · doi:10.1093/aje/kwi192 · Cited by 230
Statistical Foundations for Model-Based Adjustments
Greenland, S., & Pearce, N. E. (2015) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-031914-122559 · Cited by 274
Self-citationSemi-Automated Sensitivity Analysis to Assess Systematic Errors in Observational Data
Lash, T. L., & Fink, A. K. (2003) · Epidemiology · doi:10.1097/01.ede.0000071419.41011.cf · Cited by 250
Seeking Causal Explanations in Social Epidemiology
Kaufman, J. S., & Cooper, R. (1999) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a009969 · Cited by 257
“Randomization guarantees that FACE approaches ACE as n goes to infinity, since exposure is applied without regard to any other factors that might influence outcome (13).”
BackgroundRafi, Z., & Greenland, S. (2020) · BMC Medical Research Methodology · doi:10.1186/s12874-020-01105-9 · Cited by 243
“For example, explanations for results from randomization tests in nonrandomized studies must include not only treatment effects and random error among possible explanations, but also effects of randomization failure [86, 87].”
Self-citationCausal Inference About the Effects of Interventions From Observational Studies in Medical Journals
Dahabreh, I. J., & Bibbins-Domingo, K. (2024) · JAMA · doi:10.1001/jama.2024.7741 · Cited by 242
Statistical Control Requires Causal Justification
Wysocki, A. C., Lawson, K. M., & Rhemtulla, M. (2022) · Advances in Methods and Practices in Psychological Science · doi:10.1177/25152459221095823 · Cited by 275
“This can be done through an experimental research design in which the predictor is randomized (Greenland, 1990), but experimental manipulation of psychological variables is often unfeasible.”
BackgroundBayesian perspectives for epidemiological research. II. Regression analysis
Greenland, S. (2007) · International Journal of Epidemiology · doi:10.1093/ije/dyl289 · Cited by 200
Self-citationKrieger, N., & Smith, G. D. (2016) · International Journal of Epidemiology · doi:10.1093/ije/dyw114 · Cited by 263
He, K., Du, S., Xun, P., Sharma, S., Wang, H.-J., Zhai, F., & Popkin, B. (2011) · American Journal of Clinical Nutrition · doi:10.3945/ajcn.110.008870 · Cited by 220
CONSORT 2025 explanation and elaboration: updated guideline for reporting randomised trials
Hopewell, S., Chan, A.-W., Collins, G. S., Hróbjartsson, A., Moher, D., Schulz, K. F., Tunn, R., Aggarwal, R., Berkwits, M., Berlin, J. A., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081124 · Cited by 205
Corraini, P., Olsen, M., Pedersen, L. H., Dekkers, O. M., & Vandenbroucke, J. P. (2017) · Clinical Epidemiology · doi:10.2147/clep.s129728 · Cited by 233
“6,7 On the other hand, routinely collected health care data are an increasingly relevant source for clinical epidemiological research.”
Interval estimation by simulation as an alternative to and extension of confidence intervals.
Greenland, S. (2004) · International Journal of Epidemiology · doi:10.1093/ije/dyh276 · Cited by 202
Self-citationPerils and Potentials of Self-Selected Entry to Epidemiological Studies and Surveys
Keiding, N., & Louis, T. A. (2016) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/rssa.12136 · Cited by 186
Cole, S., Edwards, J. K., & Greenland, S. (2020) · American Journal of Epidemiology · doi:10.1093/aje/kwaa136 · Cited by 193
Self-citationAn introduction to instrumental variable assumptions, validation and estimation
Lousdal, M. L. (2018) · Emerging Themes in Epidemiology · doi:10.1186/s12982-018-0069-7 · Cited by 173
Rinsky, J. L., Nadimpalli, M. L., Wing, S., Hall, D., Baron, D., Price, L. B., Larsen, J., Stegger, M., Stewart, J. R., & Heaney, C. D. (2013) · PLoS ONE · doi:10.1371/journal.pone.0067641 · Cited by 155
“We do not report corresponding p-values because they are often interpreted incorrectly in non-randomized studies as reflecting the probability that the results would be observed by chance under the null hypothesis that no difference exists between the groups being compared [35].”
BackgroundAir Pollution and Odor in Communities Near Industrial Swine Operations
Wing, S., Horton, R. A., Marshall, S. W., Thu, K., Tajik, M., Schinasi, L. H., & Schiffman, S. S. (2008) · Environmental Health Perspectives · doi:10.1289/ehp.11250 · Cited by 179
“For the same reason, we assessed contributions of predictors to the fit of models by t-tests instead of p-values because this is not a randomized study (Greenland 1990).”
MethodInvited Commentary: The Need for Cognitive Science in Methodology
Greenland, S. (2017) · American Journal of Epidemiology · doi:10.1093/aje/kwx259 · Cited by 212
Self-citationMueller, J., Shea, K., & Daraio, C. (2015) · Materials & Design · doi:10.1016/j.matdes.2015.07.129 · Cited by 165
Identifiability, exchangeability and confounding revisited
Greenland, S., & Robins, J. M. (2009) · Epidemiologic Perspectives & Innovations · doi:10.1186/1742-5573-6-4 · Cited by 161
“Nonetheless, the framework in IEEC served as a basis for many of the more general and more extensive treatments that followed [2,3,33,35,46].”
BackgroundInfluentialSelf-citationDahabreh, I. J., Hayward, R. A., & Kent, D. M. (2016) · International Journal of Epidemiology · doi:10.1093/ije/dyw125 · Cited by 140
Using genetic markers to orient the edges in quantitative trait networks: The NEO software
Aten, J. E., Fuller, T. F., Lusis, A. J., & Horvath, S. (2008) · BMC Systems Biology · doi:10.1186/1752-0509-2-34 · Cited by 147
“Since randomization is the most convincing method for establishing causal relationships between two traits [23,24], it is natural to make use of genetically randomized genotypes (implied by Mendel's laws) to derive causality tests that are less susceptible to confounding by hidden variables [19,25-29].”
MethodHarnessing naturally randomized transcription to infer regulatory relationships among genes
Chen, L., Emmert‐Streib, F., & Storey, J. D. (2007) · Genome biology · doi:10.1186/gb-2007-8-10-r219 · Cited by 123
“Randomization is the 'gold standard' for inferring causality of one variable on another [18-20].”
BackgroundThe reporting quality of randomised controlled trials in surgery: A systematic review
Agha, R., Cooper, D., & Muir, G. (2007) · International Journal of Surgery · doi:10.1016/j.ijsu.2007.06.002 · Cited by 142
The role of causal criteria in causal inferences: Bradford Hill's "aspects of association"
Ward, A. C. (2009) · Epidemiologic Perspectives & Innovations · doi:10.1186/1742-5573-6-2 · Cited by 120
“First, following Greenland, the average of many hypothetical repetitions of a randomized control trial (RCT) will make "our estimate of the true risk difference statistically unbiased, in that the statistical expectation (average) of the estimate over the possible results equals the true value" [29].”
InfluentialPrinciples of Study Design in Environmental Epidemiology
Morgenstern, H., & Thomas, D. (1993) · Environmental Health Perspectives · doi:10.1289/ehp.93101s423 · Cited by 124
For What Applications Can Probability and Non-Probability Sampling Be Used?
Schreuder, H., Gregoire, T., & Weyer, J. (2001) · Environmental Monitoring & Assessment · doi:10.1023/a:1006316418865 · Cited by 117
“However, these data can serve useful descriptive purposes without any probabilistic interpretation (cf. Greenland, 1990, p. 6).”
BackgroundQuasi-experimental causality in neuroscience and behavioural research
Marinescu, I., Lawlor, P. N., & Kording, K. P. (2018) · Nature Human Behaviour · doi:10.1038/s41562-018-0466-5 · Cited by 107
Williams, G. M., Aardema, M., Acquavella, J., Berry, C., Brusick, D., Burns, M., de Camargo, J. D., Garabrant, D., Greim, H., Kier, L., et al. (2016) · Critical Reviews in Toxicology · doi:10.1080/10408444.2016.1214677 · Cited by 112
Describing data requires no adjustment for multiple comparisons: a reply from Savitz and Olshan.
Savitz, D., & Olshan, A. (1998) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a009532 · Cited by 112
Schneider, J. W. (2014) · Scientometrics · doi:10.1007/s11192-014-1251-5 · Cited by 112
Alcohol and mortality in middle-aged men from eastern France.
Renaud, S., Guéguen, R., Schenker, J., & d’Houtaud, A. (1998) · Epidemiology · doi:10.1097/00001648-199803000-00011 · Cited by 175
Taylor, J. A., Dominici, F., Agnew, J., Gerwin, D., Morlock, L., & Miller, M. R. (2011) · BMJ Quality & Safety · doi:10.1136/bmjqs-2011-000082 · Cited by 113
Cooper, R., & Kaufman, J. S. (1998) · Hypertension · doi:10.1161/01.hyp.32.5.813 · Cited by 98
Frequentist and Bayesian approaches to prevalence estimation using examples from Johne's disease
Messam, L. L. M., Branscum, A. J., Collins, M. T., & Gardner, I. A. (2008) · Animal Health Research Reviews · doi:10.1017/s1466252307001314 · Cited by 90
“To justify descriptive inferences and probabilistic interpretations of prevalence estimates based on sample data, random selection of units from the population to be tested is necessary (Greenland, 1990; Greiner and Gardner, 2000a).”
MethodBrothers, T., & Kuperberg, G. (2020) · Journal of Memory and Language · doi:10.1016/j.jml.2020.104174 · Cited by 101
“It is for these reasons that non-experimental data, like those reported in Smith and Levy (2013), are often considered insufficient for making causal empirical claims (Greenland et al., 1999; Greenland, 1990; Rutter, 2007).”
BackgroundMethodInterpreting the results of observational research: chance is not such a fine thing
Brennan, P., & Croft, P. (1994) · British medical journal · doi:10.1136/bmj.309.6956.727 · Cited by 101
Probability Logic and Probabilistic Induction
Greenland, S. (1998) · Epidemiology · doi:10.1097/00001648-199805000-00018 · Cited by 97
Self-citationHeuristic Thinking and Inference From Observational Epidemiology
Lash, T. (2007) · Epidemiology · doi:10.1097/01.ede.0000249522.75868.16 · Cited by 95
Miller, V., Micha, R., Choi, E., Karageorgou, D., Webb, P., & Mozaffarian, D. (2022) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.46705 · Cited by 103
For and Against Methodologies: Some Perspectives on Recent Causal and Statistical Inference Debates
Greenland, S. (2017) · European Journal of Epidemiology · doi:10.1007/s10654-017-0230-6 · Cited by 86
“In this theory, random selection and allocation allow us to equate certain observable associations with targeted effects (Greenland 1990), so that causal inference can focus on purely statistical deductions such as ‘‘if the no-effect model is correct, we would rarely see an association as or more…”
BackgroundSelf-citationBelievability of relative risks and odds ratios in abstracts: Cross sectional study.
Gøtzsche, P. C. (2006) · BMJ · doi:10.1136/bmj.38895.410451.79 · Cited by 85
Strengthening statistical usage in marine ecology
Beninger, P., Boldina, I., & Katsanevakis, S. (2012) · Journal of Experimental Marine Biology and Ecology · doi:10.1016/j.jembe.2012.05.020 · Cited by 85
“…statistics in their data treatment, and this generates seemingly meaningful numbers, but in reality such studies should rely muchmore on descriptive statistics and comparisons of effect sizes (Greenland, 1990; Rothman, 1990b), regardless of peer and reviewer pressure to the contrary.”
BackgroundGreenland, S., & Mansournia, M. A. (2015) · European Journal of Epidemiology · doi:10.1007/s10654-015-9995-7 · Cited by 86
Self-citationKaufman, J. S. (2008) · Social Science & Medicine · doi:10.1016/j.socscimed.2007.11.046 · Cited by 87
“The application of statistical reasoning in epidemiology has a clear foundation, rooted in the notion of randomization that underlies all models, tests and quantitative inferences (Greenland 1990).”
BackgroundThe map comparison problem: tests for the overlap of geographic boundaries.
Jacquez, G. (1995) · Statistics in Medicine · doi:10.1002/sim.4780142107 · Cited by 82
Remiro‐Azócar, A., Heath, A., & Baio, G. (2021) · Research Synthesis Methods · doi:10.1002/jrsm.1511 · Cited by 79
Epidemiologic measures and policy formulation: lessons from potential outcomes
Greenland, S. (2005) · Emerging Themes in Epidemiology · doi:10.1186/1742-7622-2-5 · Cited by 76
“Further details of counterfactual theory for health science research are described elsewhere [12,14-26].”
Self-citationBurra, T. A., Jerrett, M., Burnett, R., & Anderson, M. (2002) · doi:10.1111/j.1541-0064.2002.tb00737.x · Cited by 76
Confounding and Effect Modification: Distribution and Measure
VanderWeele, T. J. (2012) · Epidemiologic Methods · doi:10.1515/2161-962x.1004 · Cited by 91
“A further distinction can be drawn between confounding "in expectation" and "realized" confounding (Fisher, 1935; Rothman, 1977; Greenland, 1990; Greenland et al., 1999).”
BackgroundThe Healthy Worker Survivor Effect: Target Parameters and Target Populations
Brown, D., Picciotto, S., Costello, S., Neophytou, A. M., Izano, M. A., Ferguson, J. M., & Eisen, E. A. (2017) · Current Environmental Health Reports · doi:10.1007/s40572-017-0156-x · Cited by 78
“Such a cohort emulates features of a randomized controlled trial where follow-up time, exposure, and eligibility all start at the same time [51– 53].”
Caveats for using statistical significance tests in research assessments
Schneider, J. (2011) · J. Informetrics · doi:10.1016/j.joi.2012.08.005 · Cited by 70
“Statistical significance tests concern sampling error and we sample in order to make statistical inferences, either descriptive inferences from sample to population or causal claims (Greenland, 1990).”
BackgroundBerhane, K. T., Gauderman, W. J., Stram, D. O., & Thomas, D. C. (2004) · Statistical Science · doi:10.1214/088342304000000413 · Cited by 54
“Greenland and Morgenstern (1989) described three ways such bias can come about: (1) within-group confounding that acts differentially across groups, (2) confounding by group effects and (3) effect modification by group.”
BackgroundInfluentialUse of insurance claims databases to evaluate the outcomes of ophthalmic surgery
Coleman, A. L., & Morgenstern, H. (1997) · Survey of Ophthalmology · doi:10.1016/s0039-6257(97)00095-7 · Cited by 58
Causal Diagrams: Pitfalls and Tips
Suzuki, E., Shinozaki, T., & Yamamoto, E. (2020) · Journal of Epidemiology · doi:10.2188/jea.je20190192 · Cited by 61
The Analysis of Disease Clusters, Part I: State of the Art
Birnbaum, D., Jacquez, G., Waller, L. A., Grimson, R., & Wartenberg, D. (1996) · Infection Control & Hospital Epidemiology · doi:10.1086/647301 · Cited by 59
Randomization Does Not Help Much, Comparability Does
Saint‐Mont, U. (2015) · PLoS ONE · doi:10.1371/journal.pone.0132102 · Cited by 55
“Therefore Greenland concludes that “no matter what the outcome of randomization, the study will be completely confounded.””
BackgroundInfluentialRandom Allocation in Observational Data
Smith, G. D. (2011) · Epidemiology · doi:10.1097/ede.0b013e31821d0426 · Cited by 50
When can a clinical trial be called 'randomized'?
Berger, V., & Bears, J. D. (2003) · Vaccine · doi:10.1016/s0264-410x(02)00475-9 · Cited by 57
Basic models for disease occurrence in epidemiology.
Flanders, W., & Kleinbaum, D. (1995) · International Journal of Epidemiology · doi:10.1093/ije/24.1.1 · Cited by 57
Impact of social network on cardiovascular mortality in middle aged Danish men.
Olsen, O. (1993) · Journal of Epidemiology & Community Health · doi:10.1136/jech.47.3.176 · Cited by 50
Inpatient Palliative Care Consults and the Probability of Hospital Readmission
Nelson, C., Chand, P., Sortais, J., Oloimooja, J., & Rembert, G. (2011) · The Permanente Journal · doi:10.7812/tpp/10-142 · Cited by 54
Causality in cancer epidemiology
Λάγιου, Π., Adami, H., & Trichopoulos, D. (2005) · European Journal of Epidemiology · doi:10.1007/s10654-005-7968-y · Cited by 60
“In other words, in epidemiological research, statistical significance may be frequently overstated [19, 20].”
Background
Metadata
- Authors
- Greenland, S.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Greenland, Sander
- ORCID
- Greenland, Sander
- Venue
- Epidemiology
- Published
- 1990-11
- Volume
- 1
- Issue
- 6
- Pages
- 421-429
- ISSN
- 1044-3983 (ISSN-L)
- OpenAlex
- W2038826970
- Cited by
- 385
- References
- 0
- Citations by year
- 2026: 9 · 2025: 15 · 2024: 12 · 2023: 11 · 2022: 16 · 2021: 18 · 2020: 21 · 2019: 7 · 2018: 7 · 2017: 14 · 2016: 13 · 2015: 11 · 2014: 9 · 2013: 10 · 2012: 13
- FWCI
- 5.61
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy of Biology and Scientific Explanation
- Keywords
- causal inference, randomization, random sampling, statistical inference, data descriptors, probability models, epidemiological study design
- MeSH terms
- Bayes Theorem, Data Interpretation, Statistical, Epidemiologic Methods, Humans, Causality, Confounding Factors, Epidemiologic, 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
