Why Most Discovered True Associations Are Inflated
The DOI matches its Crossref record; 111 of the 111 references it cites were found in a registry or an index.
Abstract
Newly discovered true (non-null) associations often have inflated effects compared with the true effect sizes. I discuss here the main reasons for this inflation. First, theoretical considerations prove that when true discovery is claimed based on crossing a threshold of statistical significance and the discovery study is underpowered, the observed effects are expected to be inflated. This has been demonstrated in various fields ranging from early stopped clinical trials to genome-wide associations. Second, flexible analyses coupled with selective reporting may inflate the published discovered effects. The vibration ratio (the ratio of the largest vs. smallest effect on the same association approached with different analytic choices) can be very large. Third, effects may be inflated at the stage of interpretation due to diverse conflicts of interest. Discovered effects are not always inflated, and under some circumstances may be deflated-for example, in the setting of late discovery of associations in sequentially accumulated overpowered evidence, in some types of misclassification from measurement error, and in conflicts causing reverse biases. Finally, I discuss potential approaches to this problem. These include being cautious about newly discovered effect sizes, considering some rational down-adjustment, using analytical methods that correct for the anticipated inflation, ignoring the magnitude of the effect (if not necessary), conducting large studies in the discovery ph…
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
“Given that initial effect sizes are often inflated 61 and that we sought power to detect a difference between two groups, we doubled this estimate and aimed to test ~28 participants in each group with some attrition expected.”
From Adults with autism overestimate the volatility of the sensory environment (2017) · cites this paper as [61]
In the citing paper
“While this may reflect exaggeration of original effect sizes or publication bias (Ioannidis 2008), some degree of inflation is expected even in its absence, as our selection process filtered for original experiments with significant differences.”
From Estimating the replicability of Brazilian biomedical science (2025) · cites this paper as Ioannidis 2008
In the citing paper
“Further, in situations when an underpowered study detects a true effect, the estimate of this effect size is likely to be highly exaggerated, a phenomenon often referred to as the “winner’s curse” (15).”
From Statistical and Methodological Considerations for the Interpretation of Intranasal Oxytocin Studies (2016) · cites this paper as [15]
In the citing paper
“Researchers have strong incentives to interpret their results as supporting or extending the Bayesian framework, rather than challenging it—leading to a literature that systematically over-represents supportive evidence (Ioannidis 2008; Nosek et al. 2012).”
From The myth of the Bayesian brain (2025) · cites this paper as Ioannidis 2008
In the citing paper
“This flexibility in the synthesis of the evidence provides the assessors with the opportunity to inflate or disinflate the efficacy of a given technology, a phenomenon that was observed in scientific publications.[24]”
From Health technology assessments conducted in health care facilities: A strategic practice? Findings from a content analysis of HTA reports (2017) · cites this paper as [24]
8 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Why Most Published Research Findings Are False
Ioannidis, J. P. A. (2005) · PLoS Medicine · doi:10.1371/journal.pmed.0020124 · Cited by 10,505
Self-citationGene expression profiling predicts clinical outcome of breast cancer
van 't Veer, L. J., Dai, H., van de Vijver, M. J., He, Y. D., Hart, A. A. M., Mao, M., Peterse, H. L., van der Kooy, K., Marton, M. J., Witteveen, A. T., et al. (2002) · Nature · doi:10.1038/415530a · Cited by 9,536
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
Why Most Published Research Findings Are False
Ioannidis, J. P. A. (2005) · CHANCE · doi:10.1080/09332480.2005.10722754 · Cited by 4,702 · cited 1×
“This article will not deal with the debate on whether research findings are credible.(1) I will focus instead on the interesting subset of research findings that are true.”
BackgroundSelf-citationEffect of Rosiglitazone on the Risk of Myocardial Infarction and Death from Cardiovascular Causes
Nissen, S. E., & Wolski, K. (2007) · New England Journal of Medicine · doi:10.1056/nejmoa072761 · Cited by 4,675
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
Belief in the law of small numbers.
Tversky, A., & Kahneman, D. (1971) · Psychological Bulletin · doi:10.1037/h0031322 · Cited by 3,246
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
Internal validation of predictive models
Steyerberg, E. W., Harrell, F. E., Borsboom, G. J. J. M., Eijkemans, M. J. C., Vergouwe, Y., & Habbema, J. D. F. (2001) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(01)00341-9 · Cited by 2,746
External validity of randomised controlled trials: “To whom do the results of this trial apply?”
Rothwell, P. M. (2005) · The Lancet · doi:10.1016/s0140-6736(04)17670-8 · Cited by 2,544
Cited by
Items 701–800 of 1,004
Measuring the effects of publication bias in political science
Esarey, J., & Wu, A. (2016) · Research & Politics · doi:10.1177/2053168016665856 · Cited by 21
Herold, R., Hoffmann, W. U., & van den Berg, N. (2018) · BMC Health Services Research · doi:10.1186/s12913-018-3070-5 · Cited by 21
Chiu, C., Tollenaar, M. S., Yang, C.-T., Elzinga, B. M., Zhang, T., & Ho, H. L. (2018) · Clinical Psychological Science · doi:10.1177/2167702618804794 · Cited by 22
Problems with Statistical Practice in Human-Centric Software Engineering Experiments
Kitchenham, B. A., Madeyski, L., & Brereton, P. (2019) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3319008.3319009 · Cited by 27
Norbom, L. B., Rokicki, J., Eilertsen, E. M., Wiker, T., Hanson, J. L., Dahl, A., Alnæs, D., Fernández‐Cabello, S., Beck, D., Agartz, I., et al. (2024) · JCPP Advances · doi:10.1002/jcv2.12220 · Cited by 20
“This is not surprising as publication bias and historically small samples may have promoted inflated neurodevelopmental effects (Button et al., 2013; Ioannidis, 2008) that should be attenuated when assessing ABCD (Dick et al., 2021).”
BackgroundRate of change in carotid intima–media thickness and vascular events
Bots, M. L., Taylor, A. J., Kastelein, J. J. P., Peters, S. A. E., den Ruijter, H. M., Tegeler, C. H., Baldassarre, D., Stein, J. H., O’Leary, D. H., Revkin, J. H., et al. (2012) · Journal of Hypertension · doi:10.1097/hjh.0b013e32835644dc · Cited by 21
“Improvements in reproducibility most likely affects the absolute value of the rate of change in CIMT (closer to the true value) and certainly improves its precision [23].”
BackgroundReplication studies considered harmful
Shepperd, M. (2018) · IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER) · doi:10.1145/3183399.3183423 · Cited by 23
“Also, consider corrections to the meta-analysis [23] needed due to potential bias from inflated effect size estimates from the first study arising from publication bias [10].”
Using microRNAs as Novel Predictors of Urologic Cancer Survival: An Integrated Analysis
Chen, Z., Zhan, Y., Chi, J., Guo, S., Zhong, X., He, A., Zheng, J., Gong, Y., Li, X., & Zhou, L. (2018) · EBioMedicine · doi:10.1016/j.ebiom.2018.07.014 · Cited by 19
“It is well known that, both theoretically and empirically, smaller studies are associated with larger heterogeneity [55] and inflated effect size estimates [56, 57].”
BackgroundValstad, M., Moberget, T., Roelfs, D., Slapø, N. B., Timpe, C. M. F., Beck, D., Richard, G., Sæther, L. S., Haatveit, B. C., Skaug, K. A., et al. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117302 · Cited by 20
Tan, J., Li, L., Huang, X., Yang, C., Liang, X., Zhao, Y., Xie, J., Chen, R., Wang, D., & Xie, S. (2020) · BMJ Open · doi:10.1136/bmjopen-2020-038450 · Cited by 22
Power Calculations for Replication Studies
Micheloud, C., & Held, L. (2022) · Statistical Science · doi:10.1214/21-sts828 · Cited by 20
“In practice, publication bias and the winner’s curse often lead to overestimated original effect estimates (Ioannidis, 2008; Button et al., 2013; Anderson and Maxwell, 2017).”
BackgroundSelf-reporting Limitations in Information Systems Design Science Research: Typology and Guidelines
Barata, J., da Cunha, P. R., & de Figueiredo, A. D. (2022) · Business & Information Systems Engineering · doi:10.1007/s12599-022-00782-8 · Cited by 22
Tuyttens, F., Stadig, L. M., Heerkens, J., laer, E. V., Buijs, S., & Ampe, B. (2016) · Applied Animal Behaviour Science · doi:10.1016/j.applanim.2016.04.019 · Cited by 21
Brooks, D. R., Getz, K., Brennan, A. T., Pollack, A. Z., & Fox, M. P. (2018) · Current Epidemiology Reports · doi:10.1007/s40471-018-0147-y · Cited by 19
Quantifying prognosis with risk predictions
Pace, N. L., Eberhart, L. H. J., & Kranke, P. (2011) · European Journal of Anaesthesiology · doi:10.1097/eja.0b013e32834d9474 · Cited by 23
Putting value in biomarker research and reporting
Mischak, H., Vlahou, A., Righetti, P. G., & Calvete, J. J. (2014) · Journal of Proteomics · doi:10.1016/j.jprot.2013.12.002 · Cited by 19
Predicting individual differences in motor learning: A critical reviewPreprint
Ranganathan, R., Cone, S., & Fox, B. (2022) · PsyArXiv (OSF Preprints) · doi:10.1016/j.neubiorev.2022.104852 · Cited by 20
Bai, A. D., Wilkinson, A., Almufleh, A. S., Rai, M., Razak, F. A., Verma, A. A., & Srivastava, S. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.39893 · Cited by 19
Boshuisen, K., Brundel, M., de Kovel, C. G. F., Letteboer, T. G. W., Rinkel, G. J. E., Westermann, C. J. J., Kim, H., Pawlikowska, L., Koeleman, B. P. C., & Klijn, C. J. M. (2012) · Translational Stroke Research · doi:10.1007/s12975-012-0231-4 · Cited by 18
“Despite the reasonable power (∼80 %), it is possible that our results are false negative, caused by an overestimate of the effect size in the initial report due to the “winners curse” [13].”
Strengthening the reporting of genetic risk prediction studies (GRIPS): explanation and elaboration
Janssens, A. C. J. W., Ioannidis, J. P. A., Bedrosian, S., Boffetta, P., Dolan, S. M., Dowling, N., Fortier, I., Freedman, A. N., Grimshaw, J. M., Gulcher, J., et al. (2011) · European Journal of Epidemiology · doi:10.1007/s10654-011-9551-z · Cited by 17
“’’ [57] Explanation Assessment of the risk model in the same population as that from which the model was derived generally leads to more positive conclusions than when the evaluation is conducted in an independent population [58].”
BackgroundResultSelf-citationRochefort-Maranda, G. (2021) · Philosophical Studies · doi:10.1007/s11098-020-01424-z · Cited by 18
“…based on crossing a threshold of statistical significance and the discovery study is underpowered, the observed effects are expected to be inflated”(Ioannidis 2008, p.640) This is problematic in research contexts where the differences be- tween H0 and H1 are particularly small and where the…”
BackgroundInfluentialDetecting Evidential Value and p-Hacking With the p-Curve Tool: A Word of Caution
Erdfelder, E., & Heck, D. W. (2019) · Zeitschrift für Psychologie · doi:10.1027/2151-2604/a000383 · Cited by 22
Predicting evolutionary change at the DNA level in a natural Mimulus population
Monnahan, P. J., Colicchio, J. M., Fishman, L., Macdonald, S. J., & Kelly, J. K. (2021) · PLoS Genetics · doi:10.1371/journal.pgen.1008945 · Cited by 19
“The so called “winner’s curse” [52,53] will thus reduce the regression slope relative to 1 in Fig 2A because the allele frequency in 2014 zygotes is unaffected by estimation error in the previous generation.”
BackgroundSchlögl, M., Roller‐Wirnsberger, R., Hernes, S. S., Perkisas, S., Bakken, M. S., Miot, S., Balcı, C., Dani, M., Pajulammi, H. M., Piaggi, P., et al. (2021) · Aging Clinical and Experimental Research · doi:10.1007/s40520-021-01933-9 · Cited by 19
Wortman, J., Donnellan, M. B., & Lucas, R. E. (2014) · Archives of Scientific Psychology · doi:10.1037/arc0000007 · Cited by 19
A new wave in the genetics of psychiatric disorders: the copy number variant tsunami
Joober, R., & Boksa, P. (2009) · Journal of Psychiatry and Neuroscience · doi:10.1139/jpn.0906 · Cited by 21
Condom-Insistence Conflict in Women’s Alcohol-Involved Sexual Encounters With a New Male Partner
Bryan, A. E. B., Norris, J., Abdallah, D. A., Zawacki, T., Morrison, D. M., George, W. H., Davis, K. C., Danube, C. L., & Stappenbeck, C. A. (2016) · Psychology of Women Quarterly · doi:10.1177/0361684316668301 · Cited by 18
“Third, as previously noted, the sample size was modest, which can result in low power to detect effects and inflated parameter estimates (Button et al., 2013; Ioannidis, 2005, 2008; Zhang, Xu, & Ni, 2013).”
ResultRegnerus, M. (2016) · Social Science & Medicine · doi:10.1016/j.socscimed.2016.11.018 · Cited by 19
“This, together with the rapid expansion of publication outlets and pressure to publish, has contributed to a surge in scientific overstatements, errors, accusations of fabrications, and the issuing of errata or retractions, as well as a renewed call for greater transparency across the research process (Cumming, 2013;…”
BackgroundThe Self-Referencing task: Theoretical overview and empirical evidence
Mattavelli, S., Richetin, J., Gallucci, M., & Perugini, M. (2017) · Journal of Experimental Social Psychology · doi:10.1016/j.jesp.2017.02.006 · Cited by 20
Applications of machine learning to brain disorders
Scarpazza, C., Baecker, L., Vieira, S., & Mechelli, A. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-815739-8.00003-1 · Cited by 21
A Systematic Review on the Evolution of Power Analysis Practices in Psychological Research
Vankelecom, L., Schacht, O., Laroy, N., Loeys, T., & Moerkerke, B. (2025) · Psychologica Belgica · doi:10.5334/pb.1318 · Cited by 19
A preliminary investigation of attachment style and inflammation in African-American young adults
Ehrlich, K. B., Stern, J. A., Eccles, J. S., Dinh, J., Hopper, E. A., Kemeny, M. E., Adam, E. K., & Cassidy, J. A. (2018) · Attachment & Human Development · doi:10.1080/14616734.2018.1541516 · Cited by 19
“It is possible that our observed effect sizes are inflated due to the small sample size (Ioannidis, 2005, 2008).”
BackgroundHow effective is community-based management of freshwater resources? A review
Karres, N., Kang, S., Aldous, A. R., Pattison‐Williams, J. K., & Masuda, Y. J. (2022) · Journal of Environmental Management · doi:10.1016/j.jenvman.2022.116161 · Cited by 21
Argyrou, A., Lappas, A. S., Bakaloudi, D. R., Tsekitsidi, E., Mathioudaki, E., Michou, N., Polyzopoulou, Z. A., Christodoulou, G. N., Papazisis, G., Chourdakis, M., et al. (2023) · Psychiatry Research · doi:10.1016/j.psychres.2023.115357 · Cited by 18
Roach, J. C., Rapozo, M. K., Hara, J., Glusman, G., Lovejoy, J. C., Shankle, W. R., & Hood, L. (2023) · Journal of Alzheimer s Disease · doi:10.3233/jad-230403 · Cited by 17
The golden ratio—dispelling the myth
Naini, F. B. (2024) · Maxillofacial Plastic and Reconstructive Surgery · doi:10.1186/s40902-024-00411-2 · Cited by 17
“As such, it is possible for perpetuated and unchallenged fallacies to comprise the majority of the circulating evidence in a specific field [33].”
BackgroundUnderstanding Anomalous Gas-Phase Peak Shifts in Dip-and-Pull Ambient Pressure XPS Experiments
Teschner, D., Plescher, J., Piccinin, S., Jones, T. E., Hammud, A., Schmidt, F., Knop‐Gericke, A., Bluhm, H., & Shavorskiy, A. (2024) · The Journal of Physical Chemistry C · doi:10.1021/acs.jpcc.4c00113 · Cited by 18
Halász, G., Schmahl, J., Negron, N., Ni, M., Lim, W. K., Atwal, G. S., Bai, Y., & Glass, D. J. (2025) · Nature Communications · doi:10.1038/s41467-025-65022-5 · Cited by 20
“Underpowered mouse studies are a major factor driving the lack of reproducibility in the scienti fi c literature 3,4 .”
Tests for Gene-Environment Interactions and Joint Effects With Exposure Misclassification
Boonstra, P. S., Mukherjee, B., Gruber, S. B., Ahn, J., Schmit, S. L., & Chatterjee, N. (2016) · American Journal of Epidemiology · doi:10.1093/aje/kwv198 · Cited by 18
Visual Perceptual Load Does Not Affect the Frequency Mismatch Negativity
Wiens, S., van Berlekom, E., Szychowska, M., & Eklund, R. (2019) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.01970 · Cited by 18
“Furthermore, even if a statistically significant result reflects a true positive, the true effect size is necessarily overestimated in the context of low power (i.e., winner’s curse) (Ioannidis, 2008; Button et al., 2013).”
BackgroundContext Dependency as a Predictor of Replicability
Gollwitzer, M., & Schwabe, J. (2021) · Review of General Psychology · doi:10.1177/10892680211015635 · Cited by 18
“Other conceptually irrelevant factors include data preprocessing and/or modeling choices, such as the treatment of outliers or the inclusion of conceptually irrelevant covariates (Ioannidis, 2008; Klau et al., 2020; Patel et al., 2015).”
BackgroundEnsuring Authentic Representation and Collaboration Along with Research to Re-Design Child Welfare
Schelbe, L. A., & Geiger, J. M. (2022) · Research on Social Work Practice · doi:10.1177/10497315221074937 · Cited by 18
One finding is no finding: Toward a replication culture in family business research
Brinkerink, J., Massis, A. D., & Kellermanns, F. W. (2022) · Journal of Family Business Strategy · doi:10.1016/j.jfbs.2022.100521 · Cited by 18
Some Right Ways to Analyze (Psycho)Linguistic Data
Vasishth, S. (2022) · Annual Review of Linguistics · doi:10.1146/annurev-linguistics-031220-010345 · Cited by 19
Lies, damned lies and statistics: Clinical importance versus statistical significance in research
Mellis, C. (2017) · Paediatric Respiratory Reviews · doi:10.1016/j.prrv.2017.02.002 · Cited by 19
Coville, A., & Vivalt, E. (2017) · MetArXiv (OSF Preprints) · doi:10.31222/osf.io/5nsh3 · Cited by 17
Functional co-activation of the default mode network in APOE ε4-carriers: A replication study
Mentink, L. J., Guimaraes, J., Faber, M., Sprooten, E., Rikkert, M. G. M. O., Haak, K. V., & Beckmann, C. F. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118304 · Cited by 18
“Thirdly, in case Filippini et al. (2009) have truly discovered a non-null effect in their small sample of 36 participants, the observed effect size is likely inflated, also known as the “winner’s curse” (Button et al., 2013; Ioannidis, 2008).”
The winner's curse and related perils of low statistical power − spelled out and illustrated
Lindstromberg, S. (2023) · Research Methods in Applied Linguistics · doi:10.1016/j.rmal.2023.100059 · Cited by 17
Modelling Scientific Communities
O’Connor, C. (2023) · Cambridge University Press eBooks · doi:10.1017/9781009359535 · Cited by 28
Lower Limb Joint Mechanics during Maximal Accelerative and Decelerative Running
FITZWILLIAM, E., Steventon-Lorenzen, N., Opar, D. A., Schache, A. G., & Maniar, N. (2024) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0000000000003445 · Cited by 19
“Analysis of peak joint moments restricted to the sagittal plane (i.e., flexion/extension) for our main analysis, owing to its relevance to acceleration/deceleration (12,15,16,18).”
André, Q., & Reinholtz, N. (2024) · Journal of Consumer Research · doi:10.1093/jcr/ucae028 · Cited by 19
Weerdt, D. D., Simons, M., Struyf, E., & Tack, H. (2024) · Review of Educational Research · doi:10.3102/00346543241262807 · Cited by 22
“Second, underpowered studies that find significant results yield excessively wide sampling distributions for the sample estimates (Ioannidis, 2008).”
InfluentialThe assessment of replicability using the sum of p -values
Held, L., Pawel, S., & Micheloud, C. (2024) · Royal Society Open Science · doi:10.1098/rsos.240149 · Cited by 18
“…138 positive original studies into significant ( o ≤ threshold) and non-significant ( o > threshold) at varying thresholds. p p The proportion of significant replication studies at the one-sided 0.025 level ( r ≤ α = 0.025) is then calculated for each of the two groups and displayed in figure 2.”
MethodInfluentialMeyers, K. J., Chu, J., Mosley, T. H., & Kardia, S. L. R. (2010) · BMC Medical Genetics · doi:10.1186/1471-2350-11-160 · Cited by 16
“Follow-up searches for interaction based on this overestimated effect tend to be underpowered [44,45].”
BackgroundLiu, Y., Zhang, L., Pei, Y., Papasian, C. J., & Deng, H. (2013) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2013-1637 · Cited by 16
SALVAGING PSYCHOTHERAPY RESEARCH: A MANIFESTO
Coyne, J. C., & Kok, R. N. (2014) · Journal of Evidence-Based Psychotherapies · Cited by 19
Ewald, H., Speich, B., Ladanie, A., Bucher, H. C., Ioannidis, J. P. A., & Hemkens, L. G. (2018) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2018.11.001 · Cited by 16
Self-citationReito, A. R., Raittio, L., & Helminen, O. (2019) · PeerJ · doi:10.7717/peerj.6813 · Cited by 16
“It is clear that were we to run identical trials for each study included in both this review and in that of Khan et al. (2017), we would end up with several studies with conflicting results compared to those of the original trials owing to the poor statistical power.”
InfluentialCarbine, K. A., Lindsey, H. M., Rodeback, R. E., & Larson, M. J. (2019) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2019.06.004 · Cited by 16
Rodgers, E. M., & Franklin, C. E. (2020) · Journal of Experimental Zoology Part A Ecological and Integrative Physiology · doi:10.1002/jez.2412 · Cited by 16
Epistemic Functions of Replicability in Experimental Sciences: Defending the Orthodox View
Sikorski, M., & Andreoletti, M. (2023) · Foundations of Science · doi:10.1007/s10699-023-09901-4 · Cited by 18
“Direct replication is especially useful if the original experiment is underpowered and therefore likely to deliver an inflated effect (see e.g., Ioannidis, 2005, 2008; Pereira & Ioannidis, 2011).”
BackgroundRyan, J. L., Carrière, I., Ritchie, K. A., & Ancelin, M. (2015) · Brain and Behavior · doi:10.1002/brb3.313 · Cited by 16
“This could be explained by the “winners curse”, where a reduced effect size is commonly observed in replication studies (Ioannidis 2008).”
No Evidence That Frontal Eye Field tDCS Affects Latency or Accuracy of Prosaccades
Reteig, L. C., Knapen, T. H. J., Roelofs, F. J. F. W., Ridderinkhof, K. R., & Slagter, H. A. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00617 · Cited by 16
Scientific self-correction: the Bayesian way
Romero, F., & Sprenger, J. (2020) · Synthese · doi:10.1007/s11229-020-02697-x · Cited by 18
“This finding is in line with observations that small effects are at particular risk of being overestimated systematically (Ioannidis 2008).”
ResultLakbar, I., Poole, D., Delamarre, L., Chanques, G., Pensier, J., Monet, C., Belafia, F., Capdevila, M., JONG, A. D., & Jaber, S. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-08143-1 · Cited by 18
An empirically based power primer for laboratory aggression research
Hyatt, C. S., Crowe, M. L., West, S. J., Vize, C. E., Carter, N. T., Chester, D. S., & Miller, J. D. (2021) · Aggressive Behavior · doi:10.1002/ab.21996 · Cited by 15
Preregistration and Registered Reports in Sociology: Strengths, Weaknesses, and Other Considerations
Manago, B. N. (2023) · The American Sociologist · doi:10.1007/s12108-023-09563-6 · Cited by 18
“The file-drawer problem may result in researchers selectively reporting findings that “fit” a particular narrative (Ioannidis, 2008).”
BackgroundKlau, S., Schönbrodt, F. D., Patel, C. J., Ioannidis, J. P. A., Boulesteix, A., & Hoffmann, S. (2023) · Meta-Psychology · doi:10.15626/mp.2020.2556 · Cited by 18
Self-citationBeing Efficient About Efficacy Estimation
Senn, S. J. (2013) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2012.754726 · Cited by 16
“John Ioannidis has provided reasons why most published research findings are wrong and why those that are true in some sense are exaggerated (Ioannidis 2005, 2008).”
BackgroundEpidemiology as a liberal art: from graduate school to middle school, an unfulfilled agenda
Bracken, M. B. (2014) · Annals of Epidemiology · doi:10.1016/j.annepidem.2013.11.010 · Cited by 15
“Indeed, Ioannidis [1,2] has suggested that most research findings are inflated or false.”
BackgroundHill, W. D., Davies, G., Liewald, D. C. M., Payton, A., McNeil, C. J., Whalley, L. J., Horan, M. A., Ollier, W., Starr, J. M., Pendleton, N., et al. (2015) · Intelligence · doi:10.1016/j.intell.2015.11.005 · Cited by 16
“It is also possible that the effect size in the discovery sample was overestimated (The winner's curse) (Ioannidis, 2008) meaning that the replication sample lacked the statistical power needed for replication.”
Suspiciously High Correlations in Brain Imaging Research
Vul, E., & Pashler, H. (2017) · Wiley eBooks · doi:10.1002/9781119095910.ch11 · Cited by 15
“This procedure is biased, in that it is guaranteed to yield correlation estimates higher than the population correlation, just as publication bias (Rosenthal, 1979) will tend to yield inflated estimates of effect sizes across the published literature (Ioannidis, 2008).”
BackgroundSimple dissociations for a higher-powered neuropsychology
McIntosh, R. D. (2018) · Cortex · doi:10.1016/j.cortex.2018.03.015 · Cited by 17
“However, before adopting an effect-size index to guide theorising, we would need to give more study to the biasing effects that various factors could have upon its estimation, including control sample size, the effects of non-normality, and the selective reporting of positive dissociations: a case-control variant of t…”
BackgroundThe power of meta-analysis: a challenge for evidence-based medicine
Berchialla, P., Chiffi, D., Valente, G., & Voutilainen, A. (2020) · European Journal for Philosophy of Science · doi:10.1007/s13194-020-00321-w · Cited by 17
“4Let us note that Ioannidis (2008) pointed out that effect sizes of newly discovered true associations are essentially inflated on average if power is not considered.”
BackgroundWilliams, K. R., Wasson, S., Barrett, A. A., Greenall, R. F., Jones, S. R., & Bailey, E. G. (2021) · CBE—Life Sciences Education · doi:10.1187/cbe.20-09-0219 · Cited by 17
Transposed Conditionals, Shrinkage, and Direct and Indirect Unbiasedness
Senn, S. J. (2008) · Epidemiology · doi:10.1097/ede.0b013e318181b3e3 · Cited by 15
Market Efficiency in Asian and Australasian Stock Markets: A Fresh Look at the EvidencePreprint
Kim, J. H., Doucouliagos, H., & Stanley, T. D. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2519429 · Cited by 16
P413L CHGB is not associated with ALS susceptibility or age at onset in a Dutch population
van Vught, P. W. J., Veldink, J. H., & van den Berg, L. H. (2010) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1002512107 · Cited by 15
The myth of the Bayesian brain
Mangalam, M. (2025) · European Journal of Applied Physiology · doi:10.1007/s00421-025-05855-6 · Cited by 14
O’Hara, N. N., Slobogean, G. P., O’Halloran, K., Castillo, R. C., Sprague, S., Bhandari, M., & O’Toole, R. V. (2020) · Injury · doi:10.1016/j.injury.2020.06.050 · Cited by 18
Overestimation of benefit when clinical trials stop early: a simulation study
Liu, S., & Garrison, S. (2022) · Trials · doi:10.1186/s13063-022-06689-9 · Cited by 14
“This form of bias has been referred to as the “winner’s curse” [1].”
BackgroundSandau, N., Aagaard, T. V., Hróbjartsson, A., Harris, I. A., & Brorson, S. (2023) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2023.02.002 · Cited by 19
Xiong, X., Zhang, S., Liao, X., Du, J., Zheng, W., Hu, S., Wei, Q., & Yang, L. (2024) · Environmental Pollution · doi:10.1016/j.envpol.2024.123531 · Cited by 16
Causal Analysis of Policy Effects on Fertility
Hart, R. K., Bergsvik, J., Fauske, A., & Kim, W. (2024) · Springer eBooks · doi:10.1007/978-3-319-57365-6_451-1 · Cited by 21
Is Fluoride Potentially Neurotoxic?
Bellinger, D. C. (2019) · Archives of Pediatrics and Adolescent Medicine · doi:10.1001/jamapediatrics.2019.1728 · Cited by 15
When Shooting for the Stars Becomes Aiming for Asterisks: P -Hacking in Family Business Research
Brinkerink, J. (2021) · Entrepreneurship Theory and Practice · doi:10.1177/10422587211050354 · Cited by 16
“The systematic publication of arti fi cially produced signi fi cant results hinders scienti fi c progress (Ioannidis, 2008), as false positives are very persistent in affecting follow-up research efforts (Head et al., 2015), in particular in fi elds with weak replication cultures such as…”
BackgroundInfluentialGranot‐Hershkovitz, E., He, S., Bressler, J., Yu, B., Tarraf, W., Rebholz, C. M., Cai, J., Chan, Q. M., Garcia, T. P., Mosley, T. H., et al. (2022) · Alzheimer s & Dementia · doi:10.1002/alz.12786 · Cited by 14
“Replication of these results in independent datasets is needed in order to validate the associations and to estimate more accurate effect size estimates, that do not suffer from the Winner’s curse[6].”
Claims for improved survival from systemic corticosteroids in diverse conditions: an umbrella review
Contopoulos‐Ioannidis, D. G., & Ioannidis, J. P. A. (2011) · European Journal of Clinical Investigation · doi:10.1111/j.1365-2362.2011.02584.x · Cited by 14
Self-citationGonzález‐Pérez, A., Gayán, J., Marín, J., Galán, J. J., Sáez, M. E., Real, L. M., Antúnez, C., & Ruiz, A. (2009) · Neurogenetics · doi:10.1007/s10048-009-0170-8 · Cited by 15
“Irrespective of the statistical or biological nature of the method employed to uncover new candidate SNPs, independent replication is the only way to confirm genetic association results and to avoid false-positive signals [ 42 ].”
MethodDo Affective States Influence Risk Preferences? Evidence from Incentive-Compatible Experiments
Treffers, T., Koellinger, P., & Picot, A. O. (2016) · Schmalenbach Business Review · doi:10.1007/s41464-016-0018-3 · Cited by 16
Ratio Format Shapes Health Decisions: The Practical Significance of the “1-in-X” Effect
Sirota, M., & Juanchich, M. (2018) · Medical Decision Making · doi:10.1177/0272989x18814256 · Cited by 17
Nguyen, P. L. L., Syed, M., & McGue, M. K. (2021) · Social and Personality Psychology Compass · doi:10.1111/spc3.12628 · Cited by 16
Bertoldo, G., Callegher, C. Z., & Altoè, G. (2022) · Meta-Psychology · doi:10.15626/mp.2020.2573 · Cited by 14
Explorations in statistics: statistical facets of reproducibility
Curran‐Everett, D. (2016) · AJP Advances in Physiology Education · doi:10.1152/advan.00042.2016 · Cited by 14
“Ioannidis (23, 24) and Sterne and Davey Smith (30) discuss other things we can do.”
BackgroundInfluentialEstimating the replicability of Brazilian biomedical science
Initiative, T. B. R., Amaral, O. B., Carneiro, C. F. D., Neves, K., Sampaio, A. P. W., Gomes, B. V., Abreu, M. B. D., Tan, P. B., Mota, G. P. S., Goulart, R. N., et al. (2025) · bioRxiv · doi:10.1101/2025.04.02.645026 · Cited by 13
“…replications also limited statistical power for many experiments, even though we aimed for high power in sample size calculations (95% power to detect the original effect in each individual replication) to account for the likelihood of effect size inflation (Ioannidis, 2008; van Zwet et al., 2023).”
Quality of meta‐analyses in freshwater ecology: A systematic review
Lodi, S., Godoy, B., Ortega, J., & Bini, L. (2021) · Freshwater Biology · doi:10.1111/fwb.13695 · Cited by 10
“…of variation include the tendency of earlier studies to publish higher effect sizes (i.e. time- lag bias), publication bias, Proteus phenomenon (the attraction to contradictory results), true heterogeneity, or even chance (Ioannidis, 2008; Jennions & Møller, 2002b; Trikalinos & Ioannidis, 2006).”
BackgroundPresence and consequences of positive words in scientific abstracts
Edlinger, M., Buchrieser, F., & Wood, G. M. D. O. (2023) · Scientometrics · doi:10.1007/s11192-023-04864-6 · Cited by 15
“…journals want the most innovative and cutting-edge research results for their publications and researchers aim to publish in these journals, there is a tendency to overestimate the value and evidential value of one’s own research, i.e., to hype one’s own work (Ioannidis, 2008; Young et al., 2008).”
BackgroundEffect size benchmarks: Time for a causal renaissance
Amari, P. M., Banks, G. C., Bourque, L., Holladay-Sandidge, H. D., & O’Boyle, E. H. (2024) · The Leadership Quarterly · doi:10.1016/j.leaqua.2024.101855 · Cited by 14
Hamaya, R., Hara, K., Manson, J. E., Rimm, E. B., Sacks, F. M., Xue, Q., Qi, L., & Cook, N. R. (2025) · European Journal of Epidemiology · doi:10.1007/s10654-024-01185-7 · Cited by 14
Metadata
- Authors
- Ioannidis, J. P. A.
- Affiliations
- University of Ioannina (GR)
- Corresponding author
- Ioannidis, John P. A.
- Venue
- Epidemiology
- Published
- 2008-09
- Volume
- 19
- Issue
- 5
- Pages
- 640-648
- ISSN
- 1044-3983 (ISSN-L)
- OpenAlex
- W2150215887
- Semantic Scholar
- 0373f18622b7b64e99c7e56340ab2011dbd00b5d
- Cited by
- 1,495
- References
- 109
- Citations by year
- 2026: 91 · 2025: 87 · 2024: 78 · 2023: 112 · 2022: 94 · 2021: 99 · 2020: 103 · 2019: 131 · 2018: 108 · 2017: 101 · 2016: 87 · 2015: 77 · 2014: 72 · 2013: 60 · 2012: 50
- FWCI
- 15.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Keywords
- effect size inflation, statistical significance thresholds, underpowered studies, selective reporting, conflicts of interest, reverse bias, measurement error, replication
- MeSH terms
- Clinical Trials as Topic, Data Interpretation, Statistical, Humans, Sensitivity and Specificity, Models, Statistical, Linkage Disequilibrium, Molecular Epidemiology
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.