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 801–900 of 1,078
Lee, Y.-S., Choi, G., Han, C.-H., & Hwang, H.-J. (2026) · Journal of medical systems · doi:10.1007/s10916-026-02398-x
“To enhance the reliability of the observed neuromodulatory effects [ 56, 57 ], Wilcoxon effect sizes were computed (small: 0.1, medium: 0.3, large: 0.5).”
InfluentialPartial bodyweight-supported squats elicit eccentric contraction of the thigh muscles
Seo, E., Kim, O. V., Kim, C., Gemechu, D. T., Kim, K.-T., Kang, S. H., & Lee, S. J. (2026) · BMC Musculoskeletal Disorders · doi:10.1186/s12891-026-09917-4
“The effect size was calculated using Cohen’s d [46] for normally distributed data and Cliff’s δ [55] for non-normally distributed data.”
InfluentialElgayar, S. L. (2026) · Hong Kong Physiotherapy Journal · doi:10.1142/s1013702526500095
“Standardised e®ect sizes (Cohen's d ) were calculated from the adjusted mean di®erences 28 to quantify the magnitude of the treatment e®ect and interpreted as small ( d ¼ 0 : 2), moderate ( d ¼ 0 : 5), or large ( d ¼ 0 : 8).”
Ismayilzada, K., Topgul, K., & Tabandeh, B. (2026) · Journal of laparoendoscopic & advanced surgical techniques. Part A · doi:10.1177/10926429261450042
“14 However, subgroup analyses revealed a more nuanced pattern.”
Digital Social Networks as a Governance Mechanism: Shaping Norms for Agricultural Commodity Demand
Nguyen, N., Meyer, M. A., Kraak, M., & Drakou, E. (2026) · International Journal of the Commons · doi:10.5334/ijc.1520
Rezaeian, Z., Khaliliyan, H., Yeowell, G., & Sadeghi-demneh, E. (2026) · Spine Deformity · doi:10.1007/s43390-026-01389-9
“When meta-analysis was not possible due to outcomes reported in fewer than two studies, between-group effect sizes (Cohen’s d) with 95% CIs were calculated using reported means, standard deviations, and sample sizes [32].”
Szentimrey, Z., Ameri, G., Hong, C. X., Cheung, R., Eltahawi, A., & Ukwatta, E. (2026) · Medical Physics (Lancaster) · doi:10.1002/mp.70473
“According to Cohen in Sullivan et al., 67 an effect size greater than 0.2, represents a non-trivial difference between groups.”
InfluentialChuinsiri, N., Rungrattrakul, K., Mungngam, P., Hongboon, P., Phromrueangrit, R., Thinsathid, N., & Suksuphew, S. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15103897
“This sample size was also sufficient to detect an effect size greater than medium (rho = 0.5) in the correlation analyses [20].”
InfluentialWang, Y., Ao, J., Guo, Q.-K., Xie, Z.-Y., Fan, X., Sun, Y., Wang, Z., Wei, J., & Zeng, X.-X. (2026) · Foods · doi:10.3390/foods15101727
“Although these comparisons did not consistently reach statistical significance after FDR correction (adjusted p = 0.055), likely owing to the limited sample size (n = 4) and corresponding permutation constraints [36], these large R 2 values still indicated substantial community replacement [37].”
InfluentialChen, P.-J., & Liou, W.-K. (2026) · Clinical Simulation in Nursing · doi:10.1016/j.ecns.2026.101956
Durmuş, H. I., Solmaz, Ü., Kuşan, K. F., Kızılseki, T., & Dağ, N. (2026) · Cureus · doi:10.7759/cureus.108377
“Moreover, the large effect size observed in this study indicates that the increase in grayscale values is not only statistically significant but also clinically meaningful [18].”
Sartorio, F., Giardini, M., Libiani, G., Arcolin, I., Godi, M., & Corna, S. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15103761
“This approach was adopted to quantify the clinical relevance of the differences observed between the two orthotic conditions and the baseline, providing a more robust interpretation of the findings beyond p -values alone [43].”
Campos-Hernández, C., Romero-García, T., Frayde-Gómez, H., López-Campos, C. E., Navarro-Ibarra, M., Borbón-Román, J. C., Machado-Parra, J. P., Porras-Alvarado, V. E., & Oregel-Cortez, M. I. (2026) · Sports · doi:10.3390/sports14050204
“This highlights the importance of complementing traditional null hypothesis testing with effect size interpretation to better understand the practical relevance of training-induced adaptations, particularly in studies with relatively small sample sizes [27].”
Rana, E. (2026) · The Journal of Clinical Hypertension · doi:10.1111/jch.70285
“Relating these findings to clinically meaningful thresholds would improve their interpretability [ 7 ].”
Korte, J. A., Steele, C. J., Joiner, W., & Fan, A. P. (2026) · Human Brain Mapping · doi:10.1002/hbm.70541
“V, IX, and X (Figure 3) along with a moderate effect size, suggesting fair sensitivity (Sullivan and Feinn 2012) to aging differences.”
Felgendreff, L., Baumann, E., Habig, S., Scharbrodt, R., Kalab, M., Dempfle, A., & Hertrampf, K. (2026) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-026-06491-z
“Given the large sample size, statistically significant findings can occur for irrelevant effects lacking practical importance (Sullivan and Feinn 2012; Lakens 2013).”
Akter, T., Hoque, M., Urgeya, K. D., Stapleton, F. J., Rice, S. A., & Willcox, M. D. P. (2026) · Experimental Eye Research · doi:10.1016/j.exer.2026.111082
Keleş, E., & Özbakkaloğlu, A. (2026) · Annals of Vascular Surgery · doi:10.1016/j.avsg.2026.05.077
Keshanidokht, S., Haepers, L., Valencia, M. L., Olsen, K., Warming, A. S., Hansen, I., Putro, A. W., & Frøst, M. B. (2026) · International Journal of Gastronomy and Food Science · doi:10.1016/j.ijgfs.2026.101544
Addala, A., Ritter, V., Shaw, B. J., Bishop, F. K., Zaharieva, D. P., Hood, K. K., Prahalad, P., Unaka, N. I., Desai, M., & Maahs, D. M. (2026) · The Journal of Pediatrics · doi:10.1016/j.jpeds.2026.115156
Rajesh, S., Prabhakar, A., Eapen, C., Palaniswamy, V., Joshua, A., D'souza, M. C., & Patel, V. (2026) · Journal of Orthopaedic Surgery · doi:10.1177/10225536261440986
“24,25 Also, reliable and valid assessments were established by using McGill ’ s endurance test battery and validated core strength tests.”
Lee, H. W., Kim, H. J., Park, J. S., Lee, J. H., Park, J. J., Gwon, M., Cho, J., Seong, S. J., & Yoon, Y. (2026) · Drug Design Development and Therapy · doi:10.2147/dddt.s574016
Equivalence between FTP and RCP: Assessment of association, agreement and sex effect
Engelke, P., Vivan, L., Souza, V. R. D. A., de Lira, C. D., Weiss, K., Rosemann, T., Knechtle, B., & Andrade, M. (2026) · Clinics · doi:10.1016/j.clinsp.2026.100977
“19 The Pearson correlation coefficient was used to assess the association between FTP and RCP. Correlation strength was classified as weak (0.10 – 0.30), moderate (0.31 – 0.70), and strong ( > 0.71).”
InfluentialBenoit, V., & von Fellenberg, A. S. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1800435
Advancing sustainable human resource practices: the role of green HRM in China’s automobile sector
Wang, X.-Y., Wang, Y., & Othman, I. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07264-2
“The signi fi cance of the path relationships was evaluated using t-statistics and p-values to determine the strength of the structural associations, consistent with established statistical evaluation procedures for hypothesis testing (Sullivan and Feinn 2012).”
Andreyo, E., Unverzagt, C., Dos'santos, T., & Dawes, J. (2026) · Journal of sport rehabilitation · doi:10.1123/jsr.2024-0355
Estimating Effect Size for Mood’s Median Test
Vilakati, S., Shongwe, S. C., Mbona, S., & Dlamini, T. (2026) · Mathematics · doi:10.3390/math14091449
Parwanda, G., & Natha, H. (2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.20s.92
Moola, M., Basu, A., Kishor, M., Latha, P., & Saha, S. (2026) · International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI) · doi:10.1109/raeeucci67649.2026.11504684
“Recent ECG evaluation studies have used reporting based on effect size to place demographic differences in context and avoid overinterpretation [12], [13].”
Suwedi-Kapesa, L. C., Choko, A. T., Chirombo, J., Nothale, D., Desmond, N., & Obasi, A. I. N. (2026) · PLOS Global Public Health · doi:10.1371/journal.pgph.0006269
Moore, M. R., DeClouette, B., Chen, L., Hoffmeister, T., Ruff, G. L., Triana, J., Burke, C. J., Kaplan, D., & Youm, T. J. (2026) · HIP International · doi:10.1177/11207000261419797
“14 However, it is important to note that we identified multiple statistically significant changes in muscle CSA in our study, suggesting that our study can identify statistically significant changes.”
Daytime alertness and sleepiness as different faces of insomnia: An exploratory study
Marques, D. R., Gomes, A. A., & de Azevedo, M. H. F. (2026) · Chronobiology International · doi:10.1080/07420528.2026.2648013
“In addition, Sullivan and Feinn (2012) suggest that ORs of 1.5, 2, and 3 may be considered small, medium, and large, respectively.”
InfluentialBulte, K. R., Mitchell, L., Siegel, R., Hunter, A., Brooks, E. R., Saunders, P., & Hoffmann, S. M. (2026) · International Journal of Sports Physiology and Performance · doi:10.1123/ijspp.2025-0372
Arabic validation of the Reproductive Autonomy Scale among Egyptian women
Orabi, M., el-Gibaly, O., & Osman, D. (2026) · Journal of Egyptian Public Health Association · doi:10.1186/s42506-026-00215-4
“According to Cohen’s criteria, these represent small-to-medium effect sizes [27].”
Feizi, I., Pourfarzi, F., Faghfuri, E., Bani-Mohammad, M., & Gholizadeh, P. (2026) · Scientific Reports · doi:10.1038/s41598-026-45760-2
“…kg/m 2 ), are both statistically significant and clinically meaningful, as they exceed thresholds used in diagnostic algorithms and clinical decision-making 22,23 . minimal clinically important differences and effect sizes alongside p -values to facilitate interpretation of clinical relevance 38 .”
Laudicina, N. M., & Long, E. (2026) · The Anatomical Record · doi:10.1002/ar.70208
Szczepan, S., Wróblewska, Z., Rudnik, D., Perkins, F., Bodary, P. F., & Bottom, M. (2026) · Scientific Reports · doi:10.1038/s41598-026-48558-4
The Effects of Gamification on Students’ Academic Performance
Oliveira, W., Scaico, P. D., Hamari, J., Soltiyeva, A., Brambilla, A., & MilHosseini, S. (2026) · Technology Knowledge and Learning · doi:10.1007/s10758-026-09971-w · Cited by 6
“Due to the importance of identifying the effect size in this type of study to determine the practical significance of the findings (Sullivan, 2012), we assessed the magnitude of the difference between groups using Cohen’s d (Cohen, 1988) as an effect size measure.”
UPI/Micro-Investing Journeys and the First Green Equity: Frictions, Trust, and on-Ramp Design
Kumar, G. P., Kalyani, D., & Raju, K. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526517
“…but also considering the effect size), standardized betas and (partial) R-squared/delta R-squared are used as measures of practical magnitude [40], With controls in place, the addition of PF/TR/ORD causes increases from R2 = 0.017 to 0.208 Table 4 or an effect size change that is practically…”
InfluentialFeasibility of social media health education plus exercise in older adults with possible sarcopenia
Shi, Y., Stanmore, E., McGarrigle, L., Wang, X.-H., Gu, C., Ye, Y.-J., & Todd, C. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02585-7
“The magnitude of d_z was interpreted as: 0.2 = small, 0.5 = medium, 0.8=large, 1.3 = very large 99 .”
InfluentialDudek, D., Chrobak, A. A., Podkowa, K., Krupa, A. J., Gorostowicz, A., Jaeschke, R. R., Juryk, A., & Siwek, M. (2026) · Frontiers in Pharmacology · doi:10.3389/fphar.2026.1739359
“Therefore, reporting both p-values and effect sizes is recommended to achieve a thorough understanding of research outcomes (McGough and Faraone, 2009; Sullivan and Feinn, 2012; Ranganathan et al., 2015; Schober et al., 2018).”
Holmberg, K., Bergkvist, K., Winterling, J., Kisch, A., Wengström, Y., & Hagelin, C. L. (2026) · European Journal of Oncology Nursing · doi:10.1016/j.ejon.2026.103187
“The effect size was 0.28, indicating a small but measurable impact (Sullivan and Feinn, 2012).”
InfluentialSearles, A. R., Martin, C. W., & Reynolds, L. K. (2026) · Hydrobiologia · doi:10.1007/s10750-026-06205-z
“We defined effect sizes of 0–0.2SD as weak effects, 0.2–0.5SD as moderate effects, and > 0.5SD as strong effects (Sullivan and Feinn, 2012).”
InfluentialÇamcı, G., Oğuz, S., Uçar, G. B., & Yarman, P. (2026) · Scandinavian Journal of Caring Sciences · doi:10.1111/scs.70240
“The eta squared value is considered 0.01 (small), 0.06 (medium), and 0.14 (big) [29].”
InfluentialKwa, E., Cheong, S.-K., & Lee, P. (2026) · Journal of Visual Impairment & Blindness · doi:10.1177/0145482x261432658
“Using the Cohen approach, the effect size was categorized as follows: 0.2 (small), 0.5 (medium), and 0.8 (large) (Sullivan & Feinn, 2012).”
InfluentialBervilza, V. C., Evendi, E., Farhan, A., Wahyuni, A., & Zainuddin, Z. (2026) · Jurnal Phi; Jurnal Pendidikan Fisika dan Fisika Terapan · doi:10.22373/p-jpft.v12i2.31850
“One such test is Cohen’s d, which is widely used to measure the magnitude of the effect in comparative studies between groups (Sullivan & Feinn, 2012).”
Brown, R. B. (2026) · Nutrients · doi:10.3390/nu18081177
“Nevertheless, the effect size is the main finding of a quantitative analysis [41], and relative risks greater than 2.0 are unusually large effects for dietary factors associated with cancer risk [42].”
InfluentialLee, S.-Y., & Tak, J.-Y. (2026) · Medicina · doi:10.3390/medicina62040768
“Statistical significance was set at p 0.05 [20].”
InfluentialAndronic, O., Muri, T., Oettl, F. C., Dimitriou, D., Hoch, A., & Zingg, P. O. (2026) · Journal of Experimental Orthopaedics · doi:10.1002/jeo2.70748
“Pearson's correlation coef fi cient was used to interpret the strength of correlation according to previously published papers (e.g., small: < 0.2, medium: 0.2 – 0.5, large > 0.8) [29].”
InfluentialKitano, T., Kurosawa, N., Okamura, T., Hachisuka, S., Yamamoto, N., Nishikawa, H., Onaka, M., Suzuki, R., & Yoshida, S. (2026) · Quality of Life Research · doi:10.1007/s11136-026-04222-y
“Cohen’s effect sizes of d = 0.20, 0.50, and 0.80 was considered as small, medium, and large, respectively [22].”
InfluentialMirano, C. R., Dampil, O. C., & Tan, H. C. (2026) · Journal of the ASEAN Federation of Endocrine Societies · doi:10.15605/jafes.041.01.6243
“…equation: Sample Size based on odds ratio: where Legend: z 1-α/2 = 1.96 z 1-β = 0.842 or 1.282 OR = 3.00 (assuming that this will have large effect) 24 For the internal consistency analysis, a minimum of 104 participants was required, based on a 5% significance level, 80% power, and an assumed…”
InfluentialLiang, Y.-P., Shi, J., Cheng, X.-D., Feng, M.-Y., Jiao, D., Du, X., Ji, K., Hu, S.-B., Dong, Q., & Yang, G. (2026) · Meat Science · doi:10.1016/j.meatsci.2026.110110
Athinartrattanapong, N., Chamchoi, P., Chalermdamrichai, P., Tangkulpanich, P., Yuksen, C., Palee, C., & Seesuklom, S. (2026) · Advances in Medical Education and Practice · doi:10.2147/amep.s530106
Hassanpour, H., Nasiri, L., Mojtahed, M., Najafi-Chaleshtori, S., & Vaez-Mahdavi, M. (2026) · Annales de Toxicologie Analytique · doi:10.1016/j.toxac.2026.01.006
Now I See It‐Building Expertise in Ocular Point of Care Ultrasound
Lee, M., Chen, A. E., Davis, A. L., Tessaro, M., Moake, M., Wan, M. J., Herman, J. E., Willmott, S., Pusic, M., & Boutis, K. (2026) · AEM Education and Training · doi:10.1002/aet2.70163
“Cohen's d-effect size was also calculated [57].”
Na, J., & Niu, C.-J. (2026) · Aquatic Toxicology · doi:10.1016/j.aquatox.2026.107833
Predictive value of ultrasonographic parameters in the treatment of oral vascular anomalies.
da Silva, L. O. P., Drumond, V., de Sousa, S. F., Silva, T., Mesquita, R., & de Castro, M. A. A. (2026) · Oral surgery, oral medicine, oral pathology and oral radiology · doi:10.1016/j.oooo.2026.04.015
Brickell, T. A., Ivins, B. J., Wright, M. M., French, L. M., & Lange, R. T. (2026) · Quality of Life Research · doi:10.1007/s11136-026-04239-3
“Effect sizes present the magnitude of the effect difference in outcomes between groups [55–57 ].”
Bosbach, W., Manser, V., Bregenzer, C., Gözlügöl, N., Krieger, K., Zeimpekis, K. G., Mendes, A. F. S., Engelbrecht, S., Cardoso, Â. R. F., Shi, K., et al. (2026) · NuclearMedicine · doi:10.1055/a-2912-4818
Kartiko, D. C., Rejeki, P. S., Indarto, D., Subagio, I., Hartati, S. C. Y., Orhan, B. E., Nurwati, Y., & Pranoto, A. (2026) · Physical Education Theory and Methodology · doi:10.17309/tmfv.2026.2.16
“According to Cohen’s classification, effect sizes (Cohen’s d) were interpreted as small (d = 0.2), medium (d = 0.5), large (d = 0.8), and very large (d ≥ 1.3) to evaluate the magnitude of changes following the exercise intervention (Sullivan & Feinn, 2012).”
InfluentialInterventions addressing mental health in conflict-affected settings: A literature review
Falkbøll, N., Østergaard, M. L. D., García, J. G. Z., Canencio, D. M. A., Modvig, J. S., & Brasholt, M. (2026) · Conflict and Health · doi:10.1186/s13031-025-00746-1
“In general, effect sizes of 0.20–0.49 are considered small, 0.50–0.79 are moderate, while effect sizes of 0.80 or above are considered large [10].”
InfluentialDaosang, W., Surit, P., & Wasuntarawat, C. (2026) · Mindfulness · doi:10.1007/s12671-026-02818-6
“Effect sizes were reported using Cohen’s d for paired t -tests (small = 0.2, medium = 0.5, large = 0.8, very large = 1.3) (Sullivan & Feinn, 2012).”
InfluentialBouricha, E. M., Hakmi, M., Batlamous, B., Lkhoyaali, S., Bourais, I., Errihani, H., & Boutayeb, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-45077-0
“However, it is important to note that with a large sample size (800 frames in our case), even minor differences in binding free energy can yield extremely low p-values, potentially leading to statistical significance without practical or biological relevance 67 .”
Evensen, K. A. I., Benum, S. D., Paulsen, H., Aakvik, K., Pedersen, S. A., & Ustad, T. (2026) · Developmental Medicine & Child Neurology · doi:10.1111/dmcn.70242
Plant trait diversity buffers soil moisture dynamics on coastal dikes during drought periods
Schönebeck, J., Bunzel, D., Paul, M., & Schlurmann, T. (2026) · PLoS ONE · doi:10.1371/journal.pone.0345552
Jones, R., Devlin, N., Dalziel, K., O’Loughlin, R., Mulhern, B., White, M., Shanthikumar, S., Chen, K., Silva, M. J., Walkley, E., et al. (2026) · Archives of Disease in Childhood · doi:10.1136/archdischild-2025-329475
Adaptive background colour responses in palaemonid shrimp: a study on Cuapetes purushothamani
Naeem, U. P. M., Sureandiran, B., Chandran, R., & Kumar, T. T. A. (2026) · Marine Biology Research · doi:10.1080/17451000.2026.2615156
“The variable responses observed under green backgrounds, where some traits showed notable effect sizes without statistical significance, underscore the importance of considering both statistical significance and practical relevance when interpreting biological data (Sullivan and Feinn 2012).”
Gerbaka, L., Malaeb, D. N., Ali, A. M., Sakr, F., Dabbous, M., Fekih‐Romdhane, F., Hallit, S. R., & Obeïd, S. (2026) · Cambridge Prisms Global Mental Health · doi:10.1017/gmh.2026.10178
“A value of 0.2 reflects a weak effect, whereas values of 0.5 and 0.8 indicate a moderate and large effect size, respectively (Sullivan and Feinn, 2012).”
InfluentialPugliese, B., Hallowell, K., Vigneshwar, A., Ford, E., Connard, S. S., Love, K., & Lascelles, B. D. X. (2026) · Frontiers in Veterinary Science · doi:10.3389/fvets.2026.1760216
“Effect size describes the magnitude of a difference between two groups (e.g., treatment vs. control) allowing the practitioner to interpret the potential clinical significance of a finding (3).”
Soares, B. D. S., Mohammad, J., Cantelmo, C. E., Alves, M. C. G., Barros, B. C. D. O., & de Oliveira, G. V. (2026) · Journal of Strength and Conditioning Research · doi:10.1519/jsc.0000000000005360
Tang, Y., Zhang, X., Smith, L. M., Shkembi, A., Green, G., & Neitzel, R. L. (2026) · BMC Public Health · doi:10.1186/s12889-026-27048-2
“…relied on weighted age-adjusted odds ratios (AORs) and multivariable-adjusted odds ratios (MORs) to interpret the magnitude of associations, as these provide more meaningful insights than p-values when large sample sizes (e.g., n > 10,000) make even small differences statistically significant [26].”
Shu, H. T., Hoveidaei, A. H., Reider, L. M., Vallier, H. A., Quinnan, S. M., Gary, J. L., Carroll, E. A., Carlini, A. R., Higgins, T. F., Bosse, M. J., et al. (2026) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.25.00964
Sekibağ, O. A., & Hantal, Ş. (2026) · Journal of Back and Musculoskeletal Rehabilitation · doi:10.1177/10538127261432694
“35”
Resilience among meditators and non-meditators: a matched sample study
Wild, M. J., & Medvedev, O. N. (2026) · Mental Health Religion & Culture · doi:10.1080/13674676.2025.2584200
“However, the remaining 21 aspects were significantly different between the groups, and meditators scored significantly higher on these aspects compared to non-meditators with effect sizes (Cohen’s d ) ranging from small to moderate, (Sullivan & Feinn, 2012).”
Wang, Y., Gulzari, A., Peng, X., & Prybutok, V. R. (2026) · Asia Pacific Journal of Marketing and Logistics · doi:10.1108/apjml-03-2025-0534
Musaeus, L. H., Connelly, L. C., Bilstrup, K.-E. K., Kaspersen, M. H., & Musaeus, P. (2026) · Workshop in Primary and Secondary Computing Education · doi:10.1145/3801749.3801762
“Effect sizes (ES) and Cohen’s d values were calculated for significant results in Excel, and interpreted based on guidelines provided by Sullivan and Feinn [41, 42, 48].”
Hiestand, S., Pallesen, S., Forthun, I., Waage, S., Østbye, T., Vedaa, Ø., & Bjorvatn, B. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1771618
“Relatively large sample sizes such as ours carry the risk of identifying statistically significant differences that may be small and not clinically or practically relevant (Sullivan and Feinn, 2012).”
Riendeau, J. M., Hockerman, L., Maly, E. M., Samimi, K., & Skala, M. C. (2026) · Biophotonics discovery. · doi:10.1117/1.bios.3.3.035003
“Unless otherwise stated, statistical analysis of single variables was performed using Cohen ’ s d , 75 a measure of effect size, due to the large number of single-cell data points 76 [Eq.”
Ortega-Moody, J., Barari, G., Jenab, K., & Muldoon, W. (2026) · IEEE World Engineering Education Conference (EDUNINE) · doi:10.1109/edunine62390.2026.11547073
“Practical significance is commonly supported by effect sizes from the applied methods literature [12], [13].”
Sun, Y., Xu, Y., Kwok, T. T.-O., Sit, S. M.-M., & Lai, A. Y. K. (2026) · Mindfulness · doi:10.1007/s12671-026-02780-3 · Cited by 1
Ates, H., & Doğan, C. (2026) · Croatian Journal of Education - Hrvatski časopis za odgoj i obrazovanje · doi:10.15516/cje.v27i3.6429
“The use of a convenience sample that was not determined through a priori sample size estimation methods aligned with the research question can be considered another drawback (Cohen, 1992; Sullivan & Feinn, 2012).”
Johansen, M. W., Goddiksen, M. P., Clavien, C., Hogan, L., Olsson, I. A. S., Santos, J., dos Santos, R. A., Wall, P. J., Sandøe, P., & Lund, T. B. (2026) · PLoS ONE · doi:10.1371/journal.pone.0342227 · Cited by 3
Wang, C., Elgendi, M., & Shin, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-39875-9 · Cited by 1
Jackson, S., Burrows, A. J., Johnson, G., McCluskey, E. M., & Langen, T. A. (2026) · Ecology and Evolution · doi:10.1002/ece3.73265
“The effect size was calculated using Cohen's D, where a small effect is conventionally categorized, using the absolute value, 0.2 ≥ D ≤ 0.5, and medium effect size is 0.5 ≥ D ≤ 0.8 (Sullivan and Feinn 2012); we had no large effect sizes.”
InfluentialBarriers to Adopting Evidence From Bayesian Adaptive Clinical Trials in Critical Care
Malley, B. E., Levin, J. M., Kahn, J. M., Bukowski, L. A., & Huang, D. T. (2026) · CHEST Critical Care · doi:10.1016/j.chstcc.2026.100264 · Cited by 1
“25 Traditional interpretations of Cohen’s d are small effect size (> 0.02 and < 0.5), medium effect size (0.5–0.8), and large effect sizes (> 0.08).”
InfluentialTakla, M. N. (2026) · Journal of Manual & Manipulative Therapy · doi:10.1080/10669817.2026.2638856
“F = 2686 for time) reflect the large effect sizes observed (partial η 2 = 0.59 for PPT), which are clinically plausible for targeted, mechanism-based interventions in a well-powered study (0.95) [13].”
InfluentialAltunç, Y. E., Turan, E., Şimşek, A., & Güncan, A. (2026) · Journal of Stored Products Research · doi:10.1016/j.jspr.2025.102896
Green, A., Hardy, K., & Al-Dadah, O. (2026) · European Annals of Otorhinolaryngology Head and Neck Diseases · doi:10.1016/j.anorl.2025.12.004
Gurler, N., Şengül, T., Bülbül, S. H., Akyaz, D. Y., Güler, Ö., Yantaç, A. E., Aydın, E. B., & Kirkland‐Kyhn, H. (2026) · Nurse Education in Practice · doi:10.1016/j.nepr.2026.104789 · Cited by 4
Seo, M.-W., Ko, H., & Jung, H. (2026) · Journal of Affective Disorders · doi:10.1016/j.jad.2026.121654
Vestibular brainstem impairment following in utero exposure to high dose paracetamol
Graeca, M., Donnelly, A., Cain, L., & Kulesza, R. J. (2026) · Brain Research · doi:10.1016/j.brainres.2026.150282
Association Between Pain Subtypes and Cognitive Impairment in Parkinson’s Disease
Gao, L., Li, Z., Cai, L.-S., Xu, W., & Liu, Y. (2026) · Journal of Pain Research · doi:10.2147/jpr.s559348
“30,31 Further analysis of the risk factors for cognitive impairment indicated that the UPDRS Part III score, the HAMA score, and disease duration were the primary factors influencing cognitive function in these patients.”
Nutritional Management of Infants with Severe Bronchopulmonary Dysplasia During Acute Infection.
Thompsen, K., Murthy, K., Robinson, D. T., Baptiste, S., Li, J.-F., & Falciglia, G. H. (2026) · Jornal de Pediatria · doi:10.1016/j.jpeds.2026.115086
Effects of Scratch-Based Learning Media on Elementary Students’ Creative Skills in Social Studies
Larasati, D. A., & Roosyanti, A. (2026) · Jurnal review pendidikan dasar. Jurnal kajian pendidikan dan hasil penelitian · doi:10.26740/jrpd.v12n1.p107-115
“Because p values alone do not convey the size of a difference (Sullivan & Feinn, 2012), Cohen’s d was calculated from the t value and group sizes as d = t × √(1/ n ₁ + 1/ n ₂).”
Inflammatory markers associated with dementia: a systematic review and meta-analysis
Kuring, J. K., Mathias, J. L., Ward, L., & Tachas, G. (2026) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2026.02.044
Enhancing FinTech service acceptance: the role of quality attributes
Ullah, M. R., Chand, A., Liu, D., Khan, M. J., & Ahmed, M. S. (2026) · Digital Policy Regulation and Governance · doi:10.1108/dprg-06-2025-0195
Prevalence, extent and surrounding bone density of ankylosed impacted maxillary canines
Ong, V. X., Soh, E. X., Zakaria, N. N., Ibrahim, N., & Hassan, W. N. W. (2026) · BMC Oral Health · doi:10.1186/s12903-026-07858-x
“The effect size was interpreted as small (0.2), medium (0.5), large (0.8) and large (1.3) [17].”
InfluentialRao, A., Cholankeril, G. T., Flores, A. G., Sood, G., White, T., Kanwal, F., & El‐Serag, H. B. (2026) · Hepatology Communications · doi:10.1097/hc9.0000000000000895 · Cited by 1
“[13] A priori, we defined a ≥ 0.5-point difference on the 5-point Likert scale as clinically meaningful, consistent with previous psychometric evidence that half a SD represents a minimally important difference across rating instruments.”
InfluentialCheng, K., Qin, R., Wang, X., Wang, W., Li, H., Xiang, L., Ni, L.-P., Zhang, D., Zhang, J., & Wang, L. (2026) · Journal of Integrative Neuroscience · doi:10.31083/jin46727
“Between-group differences in both global and sub-network strength exhibited large effect sizes (Cohen’s d > 0.8) [49], which indicated that WMHs were associated with widespread alterations in RSFC, particularly in networks related to cognitive and motor function.”
Influential
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
