The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Using Effect Size—or Why the P Value Is Not Enough
Open accessAbstract
These statements about the importance of effect sizes were made by two of the most influential statistician-researchers of the past half-century. Yet many submissions to Journal of Graduate Medical Education omit mention of the effect size in quantitative studies while prominently displaying the P value. In this paper, we target readers with little or no statistical background in order to encourage you to improve your comprehension of the relevance of effect size for planning, analyzing, reporting, and understanding education research studies.In medical education research studies that compare different educational interventions, effect size is the magnitude of the difference between groups. The absolute effect size is the difference between the average, or mean, outcomes in two different intervention groups. For example, if an educational intervention resulted in the improvement of subjects' examination scores by an average total of 15 of 50 questions as compared to that of another intervention, the absolute effect size is 15 questions or 3 grade levels (30%) better on the examination. Absolute effect size does not take into account the variability in scores, in that not every subject achieved the average outcome.In another example, residents' self-assessed confidence in performing a procedure improved an average of 0.4 point on a Likert-type scale ranging from 1 to 5, after simulation training. While the absolute effect size in the first example appears clear, the effect size in the second example is less apparent. Is a 0.4 change a lot or trivial? Accounting for variability in the measured improvement may aid in interpreting the magnitude of the change in the second example.Thus, effect size can refer to the raw difference between group means, or absolute effect size, as well as standardized measures of effect, which are calculated to transform the effect to an easily understood scale. Absolute effect size is useful when the variables under study have intrinsic meaning (eg, number of hours of sleep). Calculated indices of effect size are useful when the measurements have no intrinsic meaning, such as numbers on a Likert scale; when studies have used different scales so no direct comparison is possible; or when effect size is examined in the context of variability in the population under study.Calculated effect sizes can also quantitatively compare results from different studies and thus are commonly used in meta-analyses.The effect size is the main finding of a quantitative study. While a P value can inform the reader whether an effect exists, the P value will not reveal the size of the effect. In reporting and interpreting studies, both the substantive significance (effect size) and statistical significance (P value) are essential results to be reported.For this reason, effect sizes should be reported in a paper's Abstract and Results sections. In fact, an estimate of the effect size is often needed before starting the research endeavor, in order to calculate the number of subjects likely to be required to avoid a Type II, or β, error, which is the probability of concluding there is no effect when one actually exists. In other words, you must determine what number of subjects in the study will be sufficient to ensure (to a particular degree of certainty) that the study has acceptable power to support the null hypothesis. That is, if no difference is found between the groups, then this is a true finding.Statistical significance is the probability that the observed difference between two groups is due to chance. If the P value is larger than the alpha level chosen (eg, .05), any observed difference is assumed to be explained by sampling variability. With a sufficiently large sample, a statistical test will almost always demonstrate a significant difference, unless there is no effect whatsoever, that is, when the effect size is exactly zero; yet very small differences, even if significant, are often meaningless. Thus, reporting only the significant P value for an analysis is not adequate for readers to fully understand the results.For example, if a sample size is 10 000, a significant P value is likely to be found even when the difference in outcomes between groups is negligible and may not justify an expensive or time-consuming intervention over another. The level of significance by itself does not predict effect size. Unlike significance tests, effect size is independent of sample size. Statistical significance, on the other hand, depends upon both sample size and effect size. For this reason, P values are considered to be confounded because of their dependence on sample size. Sometimes a statistically significant result means only that a huge sample size was used.3A commonly cited example of this problem is the Physicians Health Study of aspirin to prevent myocardial infarction (MI).4 In more than 22 000 subjects over an average of 5 years, aspirin was associated with a reduction in MI (although not in o
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Concerning effect size, the r-value was 0.34.This would be counted as medium effect size (Sullivan & Feinn, 2012).”
From Teaching and Learning Science Using YouTube Videos and Discovery Learning in Primary School (2020) · cites this paper as Sullivan & Feinn, 2012
Experimental — accuracy not yet measuredIn the citing paper
“effect sizes, however, are independent of sample size (Sullivan and Feinn, 2012).”
From A chatbot-delivered intervention for optimizing social media use and reducing perceived isolation among rural-living LGBTQ+ youth: Development, acceptability, usability, satisfaction, and utility (2023) · cites this paper as Sullivan and Feinn, 2012
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
An effect size primer: A guide for clinicians and researchers.
Ferguson, C. J. (2009) · Professional Psychology: Research and Practice · doi:10.1037/a0015808 · Cited by 3,467
Things I have learned (so far).
Cohen, J. (1990) · American Psychologist · doi:10.1037/0003-066x.45.12.1304 · Cited by 1,781
Beyond significance testing: Reforming data analysis methods in behavioral research.
Kline, R. B. (2004) · doi:10.1037/10693-000 · Cited by 1,034
Meta-Analysis of Multiple Primary Prevention Trials of Cardiovascular Events Using Aspirin
Bartolucci, A. A., Tendera, M., & Howard, G. (2011) · The American Journal of Cardiology · doi:10.1016/j.amjcard.2011.02.325 · Cited by 185
Research works printed but not linked: 1
- Coe R. It's the effect size, stupid: what “effect size” is and why it is important. Paper presented at the 2002 Annual Conference of the British Educational Research Association, University of Exeter, Exeter, Devon, England, September 12–14, 2002. http://www.leeds.ac.uk/educol/documents/00002182.htm. Accessed March 23, 2012.
Cited by
Sorted by citations
Items 101–200 of 1,078
Babatunde, H., McDougal, O., & Andersen, T. (2025) · Foods · doi:10.3390/foods14172996 · Cited by 13
“The absolute magnitude of d follows conventional benchmarks: values greater than 0.8 denote a large effect size, and values exceeding 1.3 are considered very large [46].”
InfluentialGholamahmadi, B., Ferreira, C. S. S., González-Pelayo, Ó., Bastos, A. C., & Verheijen, F. (2025) · Biochar · doi:10.1007/s42773-025-00483-x · Cited by 12
“Effect size refers to the raw difference between group means, or absolute effect size, as well as standardised measures of effect (Sullivan and Feinn 2012).”
Yue, Y., Lin, W. L., & Tan, H. C. (2025) · Social Responsibility Journal · doi:10.1108/srj-11-2024-0813 · Cited by 15
Proctor, C. J., Reiman, A. J., & Best, L. A. (2023) · Health Psychology and Behavioral Medicine · doi:10.1080/21642850.2023.2266220 · Cited by 11
Haverila, M. J., & Haverila, K. C. (2024) · Marketing Intelligence & Planning · doi:10.1108/mip-07-2023-0319 · Cited by 11
Vaisi-Raygani, A.-A., Moradi, M., Salari, N., Fattahi, Z., & Hadadian, F. (2025) · BMC Nursing · doi:10.1186/s12912-025-03749-8 · Cited by 14
Palacio, J. C. R., Bunn, C., & Ryo, M. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110096 · Cited by 11
Martin, S., Allen, T., Toledo-Tamula, M. A., Struemph, K., Reda, S., Wolters, P. L., Baldwin, A., Quinn, M., & Widemann, B. C. (2021) · Journal of Contextual Behavioral Science · doi:10.1016/j.jcbs.2021.10.003 · Cited by 10
Myers, W. K., Heath, G., & Rohrer, B. (2025) · Ophthalmology Retina · doi:10.1016/j.oret.2025.12.016 · Cited by 10
Immunological reference intervals in pregnancy: longitudinal analysis of adaptive lymphocyte subsets
Ângelo-Dias, M., Martins, C., Mata, M., Barata, M., Chung, A., Sarzedas, S., Fernandes, É., Appleton, C., Lima, J., & Borrego, L. M. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1634176 · Cited by 10
Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
Gong, J., Giavrimis, R., Brookes, P., Voskanyan, V., Wu, F., Ashiga, M., Truscott, M., Basios, M., Kanthan, L., Xu, J., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00295 · Cited by 5
Nicholson, W. C., Sapp, M., Miller-Karas, E., Duva, I., & Grabbe, L. (2025) · Healthcare · doi:10.3390/healthcare13111258 · Cited by 12
“For clarification, Cohen classified effect sizes as small (d = 0.2–0.4), medium (d= 0.4–0.7), and large (d = 0.8 or greater), with an effect size greater than 0.2 generally considered meaningful change [85].”
InfluentialAtuna, R., Akabanda, F., Laborde, J. A. A., Makurat, J., Bordewick-Dell, U., Lamping, M., Ritter, G., & Amagloh, F. (2025) · Critical reviews in food science and nutrition · doi:10.1080/10408398.2025.2504718 · Cited by 10
“This practice is frequently carried out in meta-analysis reviews and presented either as an odds ratio or relative risk (Ross et al. 2003; Sullivan and Feinn 2012).”
InfluentialPrevalence and burden of asthma in five European countries: a retrospective cross-sectional study
Khan, A. H., Gouia, I., Jacob-Nara, J. A., Kamat, S., Jaffe, D. H., Mackie, D. S., Balkaran, B. L., & Wisnivesky, J. P. (2025) · BMJ Open · doi:10.1136/bmjopen-2024-085175 · Cited by 11
PTSD, complex PTSD and the dissociative subtype of PTSD in patients with eating disorders
Brewerton, T. D., Nguyen, C., Bishop, N., & Dennis, K. (2025) · Journal of Eating Disorders · doi:10.1186/s40337-025-01449-x · Cited by 10
“Effect sizes are also provided, which are thought to be a better method than p-values alone of conferring clinical significance [82].”
Trbovich, A. M., Zynda, A. J., Togashi, T., Burley, C., Mucha, A., Collins, M. W., & Kontos, A. P. (2025) · Journal of Neurotrauma · doi:10.1177/08977151251359960 · Cited by 10
“Using an acceptable power (1 - b ) of 0.80, an a priori alpha level of 0.05, a medium effect size based on prior literature, 37 – 39 and a 1:1 allocation ratio, we estimated that 17 participants in BSVT and 17 in UC would be required.”
InfluentialWyplosz, B., Grenier, B., Roche, N., Roubille, F., Loubet, P., Sultan, A., Fougere, B., Fernandes, J., Duhot, D., Moulin, B., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329703 · Cited by 9
“…may have influenced the vaccine uptake), we relied on the value of the odds ratio (OR) as an effect size index that is independent of the sample size, considering that an OR = 1.5 corresponds to a small effect size, an OR = 2 to a medium effect size and an OR = 3 to a large effect size [29].”
InfluentialBettariga, F., Taaffe, D., Borsati, A., Avancini, A., Pilotto, S., Lazzarini, S., Lopez, P., Maestroni, L., Crainich, U., Bandini, E., et al. (2025) · Journal of cancer survivorship · doi:10.1007/s11764-025-01873-7 · Cited by 9
“In addition, we considered results approaching statistical significance ( p value ranging from 0.05 to 0.15) when SMD was above 0.50, with results reported as trend [35].”
InfluentialÖzyurt, F., Üzelpasacı, E., Tayfur, A., & Akbayrak, T. (2025) · BMC Women's Health · doi:10.1186/s12905-025-03881-2 · Cited by 9
“The effect size of the results was interpreted as small (d = 0.2), medium (d = 0.5), and large (d ≥ 0.8) (22).”
InfluentialBroeckel, J., Estes, L., Leonard, M., Dickerson, B. L., Gonzalez, D. E., Purpura, M., Jäger, R., Sowinski, R. J., Rasmussen, C. J., & Kreider, R. B. (2025) · Nutrients · doi:10.3390/nu17142365 · Cited by 9
“We performed a comprehensive and statistical analysis [52–54] and clinical assessment [52–58] using methods previously described in detail [59] by using International Business Machines (IBM) Statistical Package for the Social Sciences (SPSS) version 29 statistical analysis software (IBM Corp.,…”
Sogemeier, D., Naujoks, F., Forster, Y., Krems, J., & Keinath, A. (2025) · Transportation Research Part F: Traffic Psychology and Behaviour · doi:10.1016/j.trf.2025.01.041 · Cited by 9
Sleep trajectories across three cognitive‐aging pathways in community older adults
Zaheed, A. B., Tapia, A. L., Oryshkewych, N., Wheeler, B., Butters, M. A., Buysse, D. J., Leng, Y., Barnes, L. L., Lim, A., Yu, L., et al. (2025) · Alzheimer's & Dementia · doi:10.1002/alz.70159 · Cited by 9
Bracciale, A., Manso, M. C., Bracciale, F., & Costa, L. G. (2025) · Healthcare · doi:10.3390/healthcare13091020 · Cited by 9
“However, statistical power is not solely determined by sample size but also by the strength of associations observed, and several medium and large effect sizes (OR values above 2 and 3, respectively) [41] maintained methodological rigor in data collection and interpretation.”
Kanny, S., Hall, L., Blackhurst, D. W., & Sherrill, W. W. (2025) · BMC Public Health · doi:10.1186/s12889-025-22627-1 · Cited by 12
“Cohen’s d was calculated to determine the effect size of the mean change in QOL outcomes pre-to post-program (0.2 = small; 0.4 = medium; ≥ 0.8 = large) [46].”
InfluentialDominsky, O., Attali, E., Amikam, U., Gold, R., Greenberger, C., Yogev, Y., & Baruch, Y. (2025) · International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics · doi:10.1002/ijgo.70578 · Cited by 8
Chien, C.-T., & Chien, C.-H. (2025) · Sustainability · doi:10.3390/su17177944 · Cited by 8
The impact of robotic surgery on reducing radiation exposure in orthopedic trauma: a meta-analysis
Saeedi-Hosseiny, M. S., Rothenberg, H., Jadallah, A., Khaja, U., Karimov, A., & Abedin-Nasab, M. H. (2025) · Journal of Robotic Surgery · doi:10.1007/s11701-025-02454-7 · Cited by 8
“A minimum significant effect size is defined as 0.2, while a large effect size is defined as ≥ 0.8 [26].”
InfluentialMethodological foundations for artificial intelligence ‐driven survey question generation
Mburu, T., Rong, K., McColley, C. J., & Werth, A. (2025) · Journal of Engineering Education · doi:10.1002/jee.70012 · Cited by 14
“We also calculated Cohen's d to measure the effect size of these differences (Becker, 2000; Sullivan & Feinn, 2012).”
Lipnickas, G., Harris, J. M., Qesja, B., & Vos, S. D. (2025) · The Internet and Higher Education · doi:10.1016/j.iheduc.2025.101017 · Cited by 4
Hu, M., Koh, P. S., Soh, X. C., Hartanto, A., & Majeed, N. M. (2026) · Behavior Research Methods · doi:10.3758/s13428-026-02961-x · Cited by 7
“However, to facilitate a deeper comprehension of the meta-analysis script, we will also clarify key terminologies that may be less widely known below (i.e., effect sizes, measures of heterogeneity, and meta-analytic models).”
Taddio, A., Shah, V. S., McMurtry, C. M., Lang, E., MacDonald, N. E., Constantin, K. L., Uleryk, E. M., & HELPinKids&Adults Team (2026) · Clinical Journal of Pain · doi:10.1097/ajp.0000000000001371
“33 The minimum threshold of effect matched our prior work (ie, SMD ≥ 0.2).”
InfluentialTa'ani, O. A., Alhalalmeh, Y., Alabdallat, M., Naser, A., Alsakarneh, S., Saleh, S., Danpanichkul, P., Singh, D., Njei, B., & Duong, N. (2026) · Clinical and Translational Gastroenterology · doi:10.14309/ctg.0000000000000974 · Cited by 7
Chen, P. (2026) · Nurse Education Today · doi:10.1016/j.nedt.2025.106968 · Cited by 11
Tian, M.-Y., Lee, M.-H., Kim, J.-H., & Kim, M.-K. (2025) · Medicina · doi:10.3390/medicina62010090 · Cited by 7
“SMD and MD were classified as large (>0.5), medium (0.3–0.5), small (0.1–0.2), or not significant ( 0.1) between groups [30].”
InfluentialReyes-Amigo, T., Grao‐Cruces, A., Sánchez‐Oliva, D., García‐Hermoso, A., Reyes‐Molina, D., Sepulveda, R. A. Y., Arancibia, J. E. O., Almonacid, J. G. H., Páez‐Herrera, J., Salinas-Gallardo, G., et al. (2025) · Frontiers in Public Health · doi:10.3389/fpubh.2025.1644819 · Cited by 8
Jeon, E.-Y. (2025) · Teaching and Teacher Education : An International Journal of Research and Studies · doi:10.1016/j.tate.2025.105153 · Cited by 7
Hussain, I., Chauhadry, I., Umer, M., Nisa, N., Nadeem, S., Hassan, M., Sattar, A., Habib, M. A., Ariff, S., Jahangir, A., et al. (2025) · Nutrients · doi:10.3390/nu17203255 · Cited by 7
“Cohen’s h [24] was utilized to measure effect size, quantifying the magnitude of change between proportions.”
Wang, W.-Q., Li, L., Lawson, G., Li, Y., Kong, H., Yang, L., & Chen, L. (2025) · International journal of biometeorology · doi:10.1007/s00484-025-03004-4 · Cited by 7
“This study utilized Cohen's d (Sullivan and Feinn 2012 ) to assess effect size, which reflects the magnitude of differences between two populations after being influenced.”
El-Dakroury, W. A., Asaad, G. F., Shabana, M. E., Sallam, A.-A. M., AbdelRazek, M. M. M., El-Tokhy, F. S., Elbokhomy, A. S., El-Moghawry, S. A., Abdel-Malek, S. M., Abdelhay, R. W., et al. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.147321 · Cited by 7
Effect of a Multi-Faceted Training Program on Falls in Senior Pickleball Players
Myers, B., & Hanks, J. (2025) · Healthcare · doi:10.3390/healthcare13182298 · Cited by 7
“For this study, the strength of the effect size for r was defined as follows: 0.20 = small effect, 0.50 = medium effect, and 0.80 = large effect [46].”
InfluentialPrieto-González, P., Rivera-Villafuerte, A., & Canlı, U. (2025) · BMC Public Health · doi:10.1186/s12889-025-23781-2 · Cited by 7
“Effect sizes were determined using the η² (eta squared) parameter and interpreted according to the following guidelines: 0.2 indicates a small effect, 0.5 a medium effect, 0.8 a large effect, and 1.3 a very large [21].”
InfluentialJustice, L. M., Pelfrey, G. L., Foster, T. J., Brock, M., & Jiang, H. (2025) · Early Childhood Research Quarterly · doi:10.1016/j.ecresq.2025.07.002 · Cited by 11
“We consider an effect size greater than or equal to 0.35 to be meaningful given that this value is between a small and medium effect (Sullivan & Feinn, 2012) and the small to medium effect sizes found for many interventions targeting early language and social skills (e.g., Murano et al., 2020; Pak…”
InfluentialVu, T. H., & Tagliabue, M. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1602997 · Cited by 8
“This practice is in line with the recommendations of, among others, Sullivan and Feinn (79) and Maher et al. (80) and aims at enhancing transparency of fi ndings and reaching beyond the binary decision departing from the null hypothesis to include a measure of magnitude (81).”
How can we improve statistical training in archaeological science?
Vaiglova, P. (2025) · Journal of Archaeological Science · doi:10.1016/j.jas.2025.106220 · Cited by 8
Meyer, P., & Zaiser, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-04166-2 · Cited by 7
“Rather than focusing on pure significance of effects, we recommend to set focus on effect sizes (see also 106 ), which provide critical information on the magnitude of observed effects independent of sample size.”
Wang, F.-F., Meng, F., Chan, T., & Wong, S. S. C. (2025) · Pain and Therapy · doi:10.1007/s40122-025-00751-5 · Cited by 7
“This was then classified on the basis of Cohen’s benchmark: negligible ( d 0.2), small (0.2 ≤ d 0.5), moderate (0.5 ≤ d 0.8), and large ( d ≥ 0.8) [19].”
InfluentialKushlaf, H., Díaz-Manera, J., Bratkovic, D., Byrne, B. J., Claeys, K., Clemens, P. R., Dimachkie, M., Kishnani, P. S., Laforêt, P., Roberts, M., et al. (2025) · Muscle and Nerve · doi:10.1002/mus.28420 · Cited by 7
Olivier, N., Harvey, B. H., Gobec, S., Shahid, M., Košak, U., Žakelj, S., & Brink, C. B. (2025) · Biomedicine & Pharmacotherapy · doi:10.1016/j.biopha.2025.118093 · Cited by 7
The effect of marketing capabilities on marketing agility and perceived performance
Haverila, K. C., Haverila, M. J., McLaughlin, C., Mohiuddin, M., & Su, Z. (2025) · International Journal of Productivity and Performance Management · doi:10.1108/ijppm-06-2024-0388 · Cited by 10
Telehealth in treating tinnitus: a systematic review and meta-analysis
Habeeb, A., Hemaya, M., Hemaya, M., & Kanegaonkar, R. (2023) · The Journal of Laryngology & Otology · doi:10.1017/s0022215123000373 · Cited by 6
Pirbaglou, M., El Morr, C., Ahmad, F., & Ritvo, P. (2025) · JMIR Mental Health · doi:10.2196/65853 · Cited by 6
Alotaibi, N. B. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.100990 · Cited by 12
Ma, Z., Liu, H., Degen, A. A., Zhang, L., Mi, J., & Zhou, J. (2026) · Food Chemistry X · doi:10.1016/j.fochx.2026.103540 · Cited by 5
“A sample size of 6 per group resulted in a d-value close to 0.5, which is a medium and acceptable effect size (Sullivan & Feinn, 2012).”
InfluentialWijesinghe, M. S. D., Nissanka, N. A. A. D. N., Dissanayake, G., Karawita, U. G., Gunawardana, B., Weerasinghe, W. M. P. C., Rathnayaka, R. M. M. S., Mahagamage, K., Sandamali, R., Thavaseelan, R., et al. (2025) · BMC Research Notes · doi:10.1186/s13104-025-07489-5 · Cited by 6
Clarke, B., & Guida, A. M. (2025) · Journal of College Student Mental Health · doi:10.1080/28367138.2025.2552484 · Cited by 6
“Effect sizes for MANOVA follow-up Tukey analysis (Cohen’s d ) were interpreted using the general guideline for small ( d ≥0.2), medium ( d ≥0.5), and large effect sizes ( d ≥0.8) (Sullivan & Feinn, 2012).”
InfluentialKurban, Z., Khassenov, D., Burkitbayev, Z. K., Bulekbayeva, S. A., Chinaliyev, A., Serik, B., Saparbayev, S. S., Т.А., С., Zhunissova, U., Slivkina, N., et al. (2025) · Frontiers in Public Health · doi:10.3389/fpubh.2025.1590401 · Cited by 6
Vidyasagar, P., Farrell, S., Colorado, L. H., Dando, S., & Edwards, K. (2025) · Biomedicines · doi:10.3390/biomedicines13071675 · Cited by 6
“Ultimately, the overall certainty of the evidence was classified as high, moderate, low, or very low [52,53].”
Kağızmanlı, G. A., Aydın, T., Acinikli, K. Y., Işgüder, R., Karabacak, Z. K., Demir, K., Böber, E., Ünsal, Ş. E., & Abacı, A. (2025) · Journal of Clinical Research in Pediatric Endocrinology · doi:10.4274/jcrpe.galenos.2025.2025-2-17 · Cited by 6
“It was determined by calculating the standardized difference between the two means, divided by the SD for the two independent groups (19).”
Rodríguez‐Lagos, L., Fernández‐Carnero, J., Laguarta-Val, S., Serrano-García, B., Martín-Vera, D., Runge, N., & Arribas‐Romano, A. (2025) · Journal of Pain · doi:10.1016/j.jpain.2025.105464 · Cited by 7
Ângelo, D., Cardoso, H., Sanz, D., Maffìa, F., Sarkis, M., Mota, B., & Salvado, F. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14113750 · Cited by 6
“The effect sizes were calculated using Cohen’s r (continuous variables) or Cramér’s V (categorical variables), computed as small (r ≈ 0.10), medium (r ≈ 0.30), or large (r ≥ 0.50) effect sizes, according to relevant guidelines [36,37].”
InfluentialTedeschi, L. O. (2025) · Journal of Animal Science · doi:10.1093/jas/skaf136 · Cited by 6
“…in large databases, future evaluations should focus on the effect sizes and practical significance rather than solely on statistical significance (Sullivan and Feinn, 2012); adopt the use of adjusted R 2 or other less sensitive sample-size metrics (Spiess and Neumeyer, 2010), such as the robust…”
Taddio, A., Shah, V., McMurtry, C., Lang, E., MacDonald, N. E., Constantin, K. L., & Uleryk, E. (2026) · The Clinical Journal of Pain · doi:10.1097/ajp.0000000000001373 · Cited by 5
Nguyen, K., Hussain, A. S., Araujo, A. N., Strebel, L. M., Corby, T. L., Rhodes, M. A., Bruce, T. J., Cuéllar-Anjel, J., & Davis, D. (2026) · Aquaculture · doi:10.1016/j.aquaculture.2025.743021 · Cited by 5
Fagundes, F., Papasratorn, D., Elgarba, B. M., Fontenele, R., Neves, F., & Jacobs, R. (2026) · E -journal of dentistry · doi:10.1016/j.jdent.2026.106331 · Cited by 5
Experimental study of pedestrian movement characteristics on stairways under flooding emergencies
Shi, D., Chen, J., Lovreglio, R., Feng, Z., Wang, Q., & Ma, J. (2025) · Safety Science · doi:10.1016/j.ssci.2025.106980 · Cited by 6
Quality of life following total neoadjuvant therapy for rectal cancer
Wurschi, G., Diefenhardt, M., Kaufmann, J., Ha, H. M., Schneider, M., von Ohlen, D. S., Schöneich, M., Cieslak, A., Depardon, A., Becker, J., et al. (2025) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-025-06347-y · Cited by 5
“Cohen’s d > 0.2 was considered as weak, d > 0.5 as moderate, and d > 0.8 as a strong effect, respectively (New and Jersey 1988 ; Sullivan and Feinn 2012 ).”
InfluentialTan, G.-S., Ahmad, Z., & Aziz, K. A. (2025) · Tourism and Hospitality · doi:10.3390/tourhosp6040192 · Cited by 5
“An assessment of the effect size was needed as the p -value only tested the existence of effect between variables (Sullivan & Feinn, 2012). f 2 can be used to calculate effect size, with values ranging from 0.35 (large), 0.15 (medium) to 0.02 (small) (Sullivan & Feinn, 2012).”
InfluentialGhiţă, A., Hernández-Serrano, O., Fernández-Ruiz, J., Gacto‐Sánchez, M., Monràs, M., Gual, A., Porras-García, B., Ferrer‐García, M., & Gutiérrez‐Maldonado, J. (2025) · Adicciones · doi:10.20882/adicciones.1958 · Cited by 3
“The choice of a pre-established effect size of 0.5 was informed by the typical effect sizes observed in meta-analyses within the field of psychology, which tend to hover around d = 0.50 (Bakker et al., 2012; Sullivan & Feinn, 2012).”
InfluentialAlgorithmic transparency in path planning: A visual approach to enhancing human understanding
Zou, Y., & Borst, C. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103573 · Cited by 5
Senorski, R. H., Piussi, R., Högberg, J., Thomeé, R., Samuelsson, K., & Hamrin-Senorski, E. (2025) · Knee Surgery, Sports Traumatology, Arthroscopy · doi:10.1002/ksa.70042 · Cited by 5
“To interpret the clinical relevance of signi fi cant fi ndings, e ff ect sizes was calculated for numerical variables and Cohen's d was used with the following reference values: ≥ 0.20 = small, ≥ 0.50 = medium and ≥ 0.80 = large [34].”
InfluentialLiu, Q., Ho, K. Y., Lam, K. K. W., Wong, F. K. Y., Lam, W., Cheng, F. W. T., Wei, H., Chan, K., Ting, M., Yang, F. N., et al. (2025) · BMC Medicine · doi:10.1186/s12916-025-04287-5 · Cited by 5
Pan, T., Huang, L., He, V. L., Verstraete, J., Devlin, N. J., Herdman, M., & Dalziel, K. (2025) · The European Journal of Health Economics · doi:10.1007/s10198-025-01804-4 · Cited by 5
“Effect sizes of 0.2–0.49, 0.5–0.79 and ≥ 0.8 were considered small, moderate, and large respectively [32, 33 ].”
InfluentialJiang, X.-P., Li, C., Zhou, L.-J., Qiu, X.-L., Wang, W.-F., Cao, W.-J., Li, H., & Tang, L. (2025) · International Dental Journal · doi:10.1016/j.identj.2025.100896 · Cited by 5
Niknam, A., Tahmasebi, K., Hemmatinafar, M., Alkasasbeh, W. J., Willems, M. E. T., Jahromi, M. K., Kalayeh, M. B., & Zare, M. H. (2025) · Frontiers in Nutrition · doi:10.3389/fnut.2025.1559917 · Cited by 6
“Cohen’s d was used to quantify the magnitude of pairwise differences, where values of 0.2, 0.5, and 0.8 correspond to small, medium, and large effects, respectively (40).”
InfluentialRajendran, T., Patil, A., Mohanta, S. K., K, S. N., & Natarajan, V. (2025) · Journal of Public Health · doi:10.1093/pubmed/fdaf048 · Cited by 6
Dawidziuk, A., Butters, E., Lindegger, D. J., Foubister, C., Chrost, H., Wlodarski, M., Grogan, J., Rowicka, P. A., Bremner, F., & Manohar, S. G. (2025) · Diagnostics · doi:10.3390/diagnostics15091167 · Cited by 5
“An effect size of 0.92, as we obtained for VMax, is usually reported as “large” [93], enough to provide clinical utility.”
InfluentialUsing Large Language Models to Generate Concise and Understandable Test Case Summaries
Djajadi, N., Deljouyi, A., & Zaidman, A. (2025) · IEEE International Conference on Program Comprehension · doi:10.1109/icpc66645.2025.00040 · Cited by 5
“8 ) [36].”
Ghani, M. U., Gong, Y., Lin, T., Xu, Y., Zeng, T., Kamran, M., Waseem, M., & Ai, S. (2026) · BMC Plant Biology · doi:10.1186/s12870-026-08756-8 · Cited by 3
“Biochar fertilization effects were assessed using Cohen’s d to quantify the standardized mean differences between biochar treatments and urea as the baseline, emphasizing the effect size rather than relying solely on statistical significance [92], as shown in Eq.”
Nocera, S., Vegas, S., Scanniello, G., Penta, M. D., & Juristo, N. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3787786 · Cited by 2
“This effect may warrant further investigation on their causal relationship with fault-proneness [74].”
InfluentialTen common mistakes that could ruin your enrichment analysis
Bora, A., McKenzie, M., & Ziemann, M. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014122 · Cited by 4
“FDR values can tell us whether an observation is statistically significant, but it does not inform whether it is biologically impactful [22,23].”
Cementing JM ’s Impact on the Marketing Ecosystem: Empirical Execution
Steenkamp, J. B. E. M., Fischer, M., Haws, K. L., Scott, M. L., & Slotegraaf, R. J. (2026) · Journal of Marketing · doi:10.1177/00222429261426047 · Cited by 6
“…related to the effect, SS error = sum of squares related to error, SS total = total sum of squares, b = unstandardized regression coef fi cient associated with X. Sources for effect size benchmarks: Cohen (1988) for d, η 2p , f p , Φ , Cramer ’ s V, and r X , Y ; and Sullivan and Fein (2012) for OR.”
Luo, Y. T., Liu, T., Pang, P. C., McKay, D., Chang, S., & Buchanan, G. R. (2026) · Information · doi:10.3390/info17030288 · Cited by 2
Taddio, A., Shah, V., McMurtry, C., Lang, E., MacDonald, N. E., Constantin, K. L., Logeman, C., & Uleryk, E. (2026) · The Clinical Journal of Pain · doi:10.1097/ajp.0000000000001374 · Cited by 4
“19 Only results for the primary critical outcome of distress are discussed in the text of the manuscript, consistent with our prior presentation.”
Alghosi, M., Khazanin, H., Faraji, S., Uysal, H. Ş., Daneshmandi, H., Majelan, A. S., Karimi, K., Alimoradi, M., Deodato, M., & Rossettini, G. (2026) · BMC Geriatrics · doi:10.1186/s12877-026-07252-w · Cited by 4
“The ES for SB (1.82) exceeds the conventional criteria for a large effect (d ≥ 0.8) [36, 69], suggesting that approximately 88% of participants in FallProof interventions achieved better outcomes than the average participant in the control group.”
InfluentialMichels, M., Twietmeyer, J., & Musshoff, O. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101994 · Cited by 4
Nartthanarung, A., Plangsiri, K., & Kongmalai, P. (2026) · Advances in Medical Education and Practice · doi:10.2147/amep.s603679 · Cited by 4
“In contrast, our study extends prior work by incorporating a larger cohort, reporting standardized effect sizes to convey magnitude beyond statistical significance, 12 and examining cumulative improvement across sequential learning phases.”
A Critical Assessment of Bonding Descriptors for Predicting Materials Properties
Naik, A. A., Dhamrait, N., Ueltzen, K., Ertural, C., Benner, P., Rignanese, G., & George, J. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.70129 · Cited by 3
“…the number of edges in input graphs using ICOHP or ICOBI thresholds can yield sparser graphs, potentially accelerating GNN training; such computational speed-ups are expected to be significant for large datasets, although the effects on predictive performance should be carefully evaluated.”
Proper efficacy testing should be mandatory for registration of biostimulants
Termorshuizen, A., Giller, K. E., Struik, P., & Kuyper, T. W. (2026) · Outlook on Agriculture · doi:10.1177/00307270261419517 · Cited by 4
“Since statistical signi fi cance can be in fl uenced by the number of replicates, effect size is also essential (Nakagawa and Cuthill, 2007; Sullivan and Feinn, 2012).”
Beyond the p Value Dichotomy: Alternatives for Statistical Inference—A Critical Review
Ferreira, M. H. L., Câmara, L. C., & Carvas, N. (2026) · Journal of Evaluation in Clinical Practice · doi:10.1111/jep.70373 · Cited by 5
“Conversely, an effect with p = 0.051 may still be clinically relevant if its magnitude is substantial [3, 7].”
InfluentialTang, V. F. Y., Jiang, D., Kwok, J. Y. Y., Yeung, D. Y.-L., Choi, N. G., Warner, L. M., Ho, R. T. H., & Chou, K. (2026) · JAMA Network Open · doi:10.1001/jamanetworkopen.2025.57170 · Cited by 6
Wardhani, S. N., Nugraha, R., & Riansyah (2025) · Journal of Physical Education Health and Sport · doi:10.15294/jpehs.v12i2.39782 · Cited by 3
“Sullivan & Feinn, (2013) emphasized that ”the p value is limited because it does not convey the magnitude of an effect; therefore, reporting effect size is essential for understanding the practical significance of research findings.””
Processing Speed Impairment in Schizophrenia
Pratt, D. N., Linares, N. N., Spencer, C., Olson, G. M., Maeve, H., Parmacek, S. N., Lee, L. E., Alliende, L. M., Zarubin, V. C., Dickinson, D., et al. (2025) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2025.3893 · Cited by 5
Mitigating Muscle Fatigue in Upper-Limb Prosthesis Users Through Exoskeletal Weight Compensation
de Arco, L., Gusakowski, K., Cifuentes, C. A., Múnera, M. C., Segatto, M., & Díaz, C. A. R. (2025) · IEEE transactions on neural systems and rehabilitation engineering · doi:10.1109/tnsre.2025.3646061 · Cited by 4
“This suggests that the absence of statistical significance in some activities is more likely due to sample size limitations rather than the absence of a true e ff ect [36].”
Alredaini, R., Abulkhair, M., & Almisbahi, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-32373-4 · Cited by 4
“Consistent with the guidance to report effect sizes for practical interpretation rather than relying solely on p -values 46 , we summarize improvements as simple effect sizes using ∆ and % ∆ ; these are standard arithmetic definitions of absolute and relative change.”
Überall, M., Sabatowski, R., Lux, M., Heine, M., Garcia-Guerra, L., Eerdekens, M.-H., & Quandel, T. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1711597 · Cited by 4
Unraveling the physicochemical differences among Osborne protein classes via bioinformatics and AI.
Kwon, H., Xu, Y.-X., Xu, X., & Li, Y.-H. (2025) · Food Research International · doi:10.1016/j.foodres.2025.117322 · Cited by 4
de-Medeiros, L., Santibáñez, R. P. S. M., Junqueira, G. P., de Oliveira, J., Morales, S. T. T., Nogueira‐de‐Almeida, C. A., & Marchini, J. S. (2025) · Frontiers in Nutrition · doi:10.3389/fnut.2025.1701686 · Cited by 4
Montesinos, R., Olavarría, L., Henríquez, F., Chambergo‐Michilot, D., Custodio, B., Delgado, C., Málaga, M., Custodio, N., & Slachevsky, A. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1660345 · Cited by 4
Risco-Acevedo, D., Subirós, N., Camacho, H., Ramírez-Sánchez, J., Rodríguez-Virulich, Y., Etchegoyen-Amoros, A., Fuentes-Morales, D., Palenzuela, D. O., Pérez-Saad, H., & García-del-Barco-Herrera, D. (2025) · Experimental Brain Research · doi:10.1007/s00221-025-07183-9 · Cited by 3
“While effect size measures are traditionally emphasized in clinical research, the scientific community (Sullivan et al. 2012; Wasser - stein et al. 2016) increasingly recognizes their integration into preclinical studies as essential.”
Rehner, J., Gund, M., Becker, S. L., Hannig, M., Rupf, S., Schattenberg, J., Keller, A., Molano, L.-A. G., & Keller, V. (2025) · Nutrients · doi:10.3390/nu17223527 · Cited by 4
“Because p -values can be misleading or show only an incomplete picture of the actual differences [26–28] (e.g., they do not convey the magnitude of an effect, can be influenced by sample size, and are susceptible to misinterpretation) and fold changes can likewise be mis-leading (e.g., due to their…”
Metadata
- Authors
- Sullivan, G. M., & Feinn, R.
- Affiliations
- University of Connecticut (US)
- Corresponding author
- Sullivan, Gail M.
- Venue
- Journal of Graduate Medical Education
- Published
- 2012-09
- Volume
- 4
- Issue
- 3
- Pages
- 279-282
- ISSN
- 1949-8349 (ISSN-L)
- 1949-8357
- PMC
- PMC3444174
- OpenAlex
- W2107026277
- Cited by
- 5,553
- References
- 6
- Citations by year
- 2026: 607 · 2025: 877 · 2024: 759 · 2023: 547 · 2022: 574 · 2021: 499 · 2020: 416 · 2019: 419 · 2018: 320 · 2017: 222 · 2016: 215 · 2015: 83 · 2014: 9 · 2013: 4 · 2012: 2
- FWCI
- 35.75
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Journal of Graduate Medical Education (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (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
- Social Sciences › Education › Educational Research and Methods
- Keywords
- effect size, p-values, statistical significance, substantive significance, standardized mean difference, medical education research, educational intervention, meta-analysis, simulation-based training, resident confidence, test scores, interpretation of study results, graduate medical education, reporting guidelines
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
