The DOI matches its Crossref record; 59 of the 62 references it cites were found in a registry or an index.
Fixed or random effects meta-analysis? Common methodological issues in systematic reviews of effectiveness
Abstract
Systematic review aims to systematically identify, critically appraise, and summarize all relevant studies that match predefined criteria and answer predefined questions. The most common type of systematic review is that assessing the effectiveness of an intervention or therapy. In this article, we discuss some of the common methodological issues that arise when conducting systematic reviews and meta-analyses of effectiveness data, including issues related to study designs, meta-analysis, and the use and interpretation of effect sizes.
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
“Additionally, it was recommended that the protocol should define the methods to be used for risk of bias assessment, meta-analysis and exploration of heterogeneity [41, 42, 44].”
From Methods to systematically review and meta-analyse observational studies: a systematic scoping review of recommendations (2018) · cites this paper as [44]
In the citing paper
“The articles recommended that the protocol should state the objectives, hypotheses to be tested and the rationale of the review, [29] and that it should describe eligibility criteria [29, 33, 35, 36, 38, 39, 41], define the type of studies to be included [35, 37, 42, 44], and give the reason when including observational studies in the review [35, 37, 40].”
From Methods to systematically review and meta-analyse observational studies: a systematic scoping review of recommendations (2018) · cites this paper as [44]
In the citing paper
“Twenty-five (27%) articles gave recommendations on item “considering different study designs” [8, 29, 34, 35, 37–39, 42, 44, 49, 51, 56, 61, 65, 70, 73, 75, 76, 77–83], with publication dates between 1995 and 2016 (median year of publication 2007).”
From Methods to systematically review and meta-analyse observational studies: a systematic scoping review of recommendations (2018) · cites this paper as [44]
In the citing paper
“A variation of this recommendation was to exclude studies that are at high risk of bias [42, 44, 54, 73, 82].”
From Methods to systematically review and meta-analyse observational studies: a systematic scoping review of recommendations (2018) · cites this paper as [44]
Citations
Cites
Cochrane Handbook for Systematic Reviews of Interventions: Cochrane Book Series
(2008) · doi:10.1002/9780470712184 · Cited by 25,048
(2000) · Cited by 9,198
A basic introduction to fixed-effect and random-effects models for meta-analysis
Borenstein, M., Hedges, L. V., Higgins, J. P. T., & Rothstein, H. R. (2010) · Research Synthesis Methods · doi:10.1002/jrsm.12 · Cited by 6,793
Methods of Meta-Analysis: Correcting Error and Bias in Research Findings
Schmidt, F. L., & Hunter, J. E. (2015) · doi:10.4135/9781483398105 · Cited by 5,542
The Handbook of Research Synthesis and Meta-Analysis
(2019) · doi:10.7758/9781610448864 · Cited by 4,553
Morris, S. B., & DeShon, R. P. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.1.105 · Cited by 2,502
Systematic Reviews in Health Care : Meta-Analysis in Context
Egger, M., Smith, G. D., & Altman, D. G. (2000) · Cited by 2,312
Meta-analyses involving cross-over trials: methodological issues
Elbourne, D. R., Altman, D. G., Higgins, J. P., Curtin, F., Worthington, H. V., & Vail, A. (2002) · International Journal of Epidemiology · doi:10.1093/ije/31.1.140 · Cited by 2,305
Hayes, R., & Moulton, L. H. (2009) · Chapman & Hall/CRC eBooks · doi:10.1201/9781584888178 · Cited by 881
15 Design and Analysis of Cross-Over Trials
Kenward, M. G., & Jones, B. C. (2007) · Handbook of statistics · doi:10.1016/s0169-7161(07)27015-4 · Cited by 873
Research works printed but not linked: 3
- Walter, 1998, Odds ratios revisited., Evidence-Based Med, 3, 71
- Olkin, 1998, Odds ratios revisited., Evidence-Based Med, 3, 71
- Altman, 1998, Odds ratios revisited., Evidence-Based Med, 3, 71
Cited by
Sorted by citations
Items 301–400 of 1,000
Brush, P. L., Sherman, M. B., & Lambrechts, M. J. (2023) · Clinical Spine Surgery A Spine Publication · doi:10.1097/bsd.0000000000001534 · Cited by 17
Koh, J. H., Yeo, B. S. Y., Tan, T. W. E., See, M. Y. S., Ng, A. C. W., Loh, S. R. H., Gooley, J. J., Tan, C. S., & Toh, S. T. (2024) · Clinical Kidney Journal · doi:10.1093/ckj/sfae177 · Cited by 19
“Random-effects models were used in all analysis regardless of heterogeneity as recent evidence suggests that it provides more robust outcome measures compared to the alternative fixed effects models [35 ].”
MethodTeo, A. Y. T., Yau, C. E., Low, C. E., Pereira, J. V., Ng, J. Y. X., Soong, T. K., Lo, Y. T., & Yang, V. S. (2024) · EClinicalMedicine · doi:10.1016/j.eclinm.2024.102870 · Cited by 17
“A random-effects model was applied in all analyses due to the high clinical likelihood that the included study populations are heterogeneous, 56,57 and to allow generalisation of the results beyond the included studies.”
MethodHopper, S. I., Murray, S. L., Ferrara, L. R., & Singleton, J. K. (2018) · The JBI Database of Systematic Reviews and Implementation Reports · doi:10.11124/jbisrir-2017-003477 · Cited by 17
“The choice of model (random or fixed effects) and method for meta-analysis will be based on the guidance by Tufanaru et al.(25) Where statistical pooling is not possible, the findings will be presented in narrative form including tables and figures to aid in data presentation where appropriate.”
MethodGao, Y., & Liu, N. (2025) · Geriatric Nursing · doi:10.1016/j.gerinurse.2025.05.005 · Cited by 16
Khalafi, M., Maleki, A. H., Symonds, M. E., Alamdari, K. A., Ehsanifar, M., & Rosenkranz, S. K. (2025) · Obesity Reviews · doi:10.1111/obr.13954 · Cited by 18
Lim, S. Y., Wang, R., Tan, D. J. H., Ng, C. H., Lim, W. H., Quek, J., Syn, N. L. X., Nah, B. K. Y., Wong, E. T. Y., Huang, D. Q., et al. (2021) · Transplant International · doi:10.1111/tri.14149 · Cited by 18
Impacto psicológico da COVID-19 nos profissionais de saúde: revisão sistemática de prevalência
Sousa, L., Albuquerque, J. M., Cunha, M., & Santos, E. J. F. (2021) · Acta Paulista de Enfermagem · doi:10.37689/acta-ape/2021ar03775 · Cited by 17
“As análises estatísticas incluíram modelos de efeitos aleatórios apenas na presença de heterogeneidade moderada a elevada (I2>50%) e, na sua ausência, modelos de efeitos fixos.(18)”
Li, N., Guo, X., Sun, C., Lowe, S., Su, W., Song, Q., Wang, H., Liang, Q., Liang, M., Ding, X., et al. (2022) · Nutrition Research · doi:10.1016/j.nutres.2022.01.004 · Cited by 16
Katsaras, D. N., Katsaras, G. Ν., Chatziravdeli, V., Papavasileiou, G., Touloupaki, M., Mitsiakos, G., Doxani, C., Stefanidis, I., & Dardiotis, E. (2022) · British Journal of Clinical Pharmacology · doi:10.1111/bcp.15291 · Cited by 16
“The main analysis, along with the prespecified subgroup analyses, was performed using the random effect model due to the intrinsic heterogeneity of the large number of studies and because the aim of our meta-analysis was to generalize the results beyond the included studies.(18) Outcomes with zero events in both arms…”
MethodYeo, B. S. Y., Koh, J. H., Tan, B. K. J., Ding, Y., Teo, Y. H., Alkan, U., See, A., Loh, S. R. H., & Toh, S. T. (2022) · JAMA Otolaryngology–Head & Neck Surgery · doi:10.1001/jamaoto.2022.2285 · Cited by 17
Fontes, A. F. D. S., dos Reis, F. M., Cândido, A. L., Gomes, K. B., & Tosatti, J. A. G. (2023) · European Journal of Clinical Pharmacology · doi:10.1007/s00228-023-03461-z · Cited by 16
“The results were presented as standardized mean difference (SMD) with a 95% confidence interval (CI) as a measure of effect, given the possible differences in the methods of measuring the markers between the included studies [29-31].”
MethodYu, J., Liu, X., Zhu, Z., Yang, Z., He, J., Zhang, L., & Lu, H. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1138234 · Cited by 16
“If a model was validated in two or more studies, we applied a random effects meta-analysis model to evaluate discrimination performance (26).”
MethodZhu, R., Xu, H., Cai, H., Wang, S., Mao, J., Zhang, J., Xiong, X., Wang, X., Zhou, W., & Guo, L. (2023) · Nutrition Metabolism and Cardiovascular Diseases · doi:10.1016/j.numecd.2023.04.020 · Cited by 18
Renal safety of critical care sedation with sevoflurane: a systematic review and meta-analysis
Taylor, B., Scott, T. E., Shaw, J., & Chockalingam, N. (2023) · Journal of Anesthesia · doi:10.1007/s00540-023-03227-y · Cited by 15
“A common-effects model was used for outcomes reported by five or fewer studies, provided that the studies were not clinically and statistically heterogeneous [41].”
MethodKoh, J. H., Lim, C. Y. J., Tan, L. T. P., Makmur, A., Gao, E. Y., Ho, J. S. Y., Tan, J. A., See, A., Tan, B. K. J., Tan, L. F., et al. (2024) · Annals of Surgical Oncology · doi:10.1245/s10434-024-15510-7 · Cited by 16
“23 When three of more studies were available, 95% prediction intervals (PIs) were computed to estimate the potential range of true effect sizes across individual studies, given that the 95% confidence interval (CI) only accounts for the uncertainty of the mean effect size, not the uncertainty of…”
Madebo, M. P., Ayalew, Y., Zheng, Y., & Jin, P. (2022) · Food Reviews International · doi:10.1080/87559129.2022.2122995 · Cited by 16
Zhou, L., Li, H., Li, M., & Liu, L. (2023) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-022-00960-9 · Cited by 18
“Random-effect model was used for evidence synthesis when more than five studies were included, otherwise, the fixed-effect model was used [20, 21] Besides, heterogeneity would be taken into account for statistical model choice when necessary.”
MethodGalea, C., Jones, A., Ko, K., Salins, A., Robidoux, S., Noble, C., & McArthur, G. (2025) · Frontiers in Language Sciences · doi:10.3389/flang.2025.1540562 · Cited by 21
Wang, L., Montgomery, A., Smerdely, P., Paulik, O., Barton, C., Halcomb, E., Hui, H., Pieri, C., Lopez, M. R., Teus, J. K., et al. (2025) · Age and Ageing · doi:10.1093/ageing/afaf117 · Cited by 26
A systematic review on self-management education campaigns for back pain
Nkhata, L. A., Brink, Y., Ernstzen, D. V., & Louw, Q. A. (2019) · South African Journal of Physiotherapy · doi:10.4102/sajp.v75i1.1314 · Cited by 18
Seroprevalence of Bovine Brucellosis in Ethiopia: Systematic Review and Meta-Analysis
Gessese, A. T., Dejene, H., Admassu, B., Adugna, T., Ali, D. A., Dagnaw, G. G., & Bitew, A. B. (2021) · Veterinary Medicine Research and Reports · doi:10.2147/vmrr.s289721 · Cited by 15
Hu, Y., Ai, L., & Zhou, L. (2021) · PLoS ONE · doi:10.1371/journal.pone.0251202 · Cited by 15
“The radom-effect model was applied in our meta—analysis, however, the estimation of betweenstudy variance might not be precise [25,26].”
MethodWang, Y., Song, Z., Xu, X., Wei, X., Yuan, H., Liang, H., & Wen, H. (2022) · Acta Tropica · doi:10.1016/j.actatropica.2022.106481 · Cited by 15
Abi‐Jaoude, J., Naiem, A. A., Edwards, T. A., Lukaszewski, M., Obrand, D. I., Steinmetz, O. K., Bayne, J. P., MacKenzie, K. S., Gill, H. L., & Girsowicz, E. (2022) · European Journal of Vascular and Endovascular Surgery · doi:10.1016/j.ejvs.2022.04.020 · Cited by 15
Executive (dys)functions and ODD and CD: A systematic review and meta-analysis.
Figueiredo, P., Ramião, E., Barroso, R., & Barbosa, F. (2022) · Neuropsychology · doi:10.1037/neu0000881 · Cited by 17
Lim, W. H., Tan, C., Xiao, J., Tan, D. J. H., Ng, C. H., Yong, J. N., Fu, C. E., Chan, K. E., Zeng, R. W., Ren, Y. P., et al. (2023) · Liver Transplantation · doi:10.1097/lvt.0000000000000004 · Cited by 15
“[19,20] Random effects model was used in all analyses regardless of heterogeneity measures as evidence has demonstrated more robust effect estimates with random effect compared with fixed effect models.[21,22] An analysis of proportions was pooled using a generalized linear mixed model with ClopperPearson intervals to…”
MethodChung, S. P., Nehme, Z., Johnson, N. J., Lagina, A. T., & Bray, J. (2023) · Resuscitation Plus · doi:10.1016/j.resplu.2023.100398 · Cited by 15
“We used a random effect model for pooled analyses because this method incorporates the influence of potential heterogeneity and retrieves a more generalized result.(34) A previous systematic review by Sahu et al.”
MethodSood, N., Sangari, A., Goyal, A., Sun, C., Horinek, M., Hauger, J. A., & Perry, L. (2023) · World Journal of Cardiology · doi:10.4330/wjc.v15.i10.531 · Cited by 15
Quality of Life After Percutaneous Coronary Intervention Versus Coronary Artery Bypass Grafting
Dimagli, A., Spadaccio, C., Myers, A. C., Demetres, M., Rademaker-Havinga, T., Stone, G., Spertus, J., Redfors, B., Fremes, S. E., Gaudino, M., et al. (2023) · Journal of the American Heart Association : Cardiovascular and Cerebrovascular Disease · doi:10.1161/jaha.123.030069 · Cited by 16
Luo, X., Guo, Y., Yu, H., Li, S., & Yin, X. (2017) · Nursing and Health Sciences · doi:10.1111/nhs.12361 · Cited by 15
Li, T., Zhang, H., An, G., Lan, H., Xu, Y., Ge, Y., & Yao, J. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.739263 · Cited by 15
Atlaw, D., Shiferaw, Z., Sahiledengle, B., Degno, S., Mamo, A., Zenbaba, D., Gezahegn, H., Desta, F., Negash, W., Assefa, T., et al. (2022) · PLoS ONE · doi:10.1371/journal.pone.0271313 · Cited by 21
“The random-effects model was used to analyze the data because the heterogeneity is high, and 22 studies were included in this metaanalysis [37, 38].”
MethodSaganski, G. F., & Freire, M. H. D. S. (2019) · The JBI Database of Systematic Reviews and Implementation Reports · doi:10.11124/jbisrir-2017-003696 · Cited by 15
Mediana, N., Funa, A., & Dio, R. (2025) · International Journal of Education in Mathematics, Science and Technology · doi:10.46328/ijemst.4769 · Cited by 42
Nuccio, E., Petrosino, F., Simeone, S., Alvaro, R., Vellone, E., & Pucciarelli, G. (2023) · Disability and Rehabilitation · doi:10.1080/09638288.2023.2287016 · Cited by 15
“Any differences between investigators were discussed or settled with the help of a third one (GP), with particular expertise in qualitative research methods, to determine disagreements and agreement [23].”
Nairn, B., Koohi, N., Kaski, D. N., Bamiou, D., & Pavlou, M. (2025) · Journal of the American Heart Association · doi:10.1161/jaha.124.040663 · Cited by 19
Park, B.-M. (2021) · Healthcare · doi:10.3390/healthcare9060699 · Cited by 14
“Assuming that each research had its own effect, calculations were performed using a random effects model that reset the weight because the homogeneity of the effect size was not secured [28,29].”
MethodSeasonal Shifts in Children’s Sedentary Behaviors, Physical Activity, and Sleep
Weaver, R. G., Hensing, C., Armstrong, B., Adams, E. L., & Beets, M. W. (2022) · Pediatric Clinics of North America · doi:10.1016/j.pcl.2022.04.005 · Cited by 14
Chen, V., Zurbau, A., Ahmed, A., Khan, T. A., Au‐Yeung, F., Chiavaroli, L., Mejía, S. B., Leiter, L. A., Jenkins, D. J. A., Kendall, C. W. C., et al. (2022) · BMJ Open Diabetes Research & Care · doi:10.1136/bmjdrc-2022-002784 · Cited by 17
Kisielinski, K., Hirsch, O., Wagner, S., Wojtasik, B., Funken, S., Klosterhalfen, B., Manna, S. K., Prescher, A., Sukul, P., & Sönnichsen, A. C. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1125150 · Cited by 14
“As we anticipated a considerable between-study heterogeneity the random effects model was used to pool effect sizes (40).”
MethodRetractedHu, L., Du, X., Jiang, Z., Song, C., & Liu, D. (2023) · European Journal of Clinical Pharmacology · doi:10.1007/s00228-023-03545-w · Cited by 14
“Tuafanaru [18] had suggested four criteria for the choice of a fixed effects model or a random effects model, the first criterion to be considered for the study being the objective of the statistical inference, whether we want to generalize the results beyond the research literature, and if so, then it is more appropr…”
Farisoğulları, B., Santos, E. J. F., Dures, E. K., Geenen, R., & Machado, P. (2023) · RMD Open · doi:10.1136/rmdopen-2023-003349 · Cited by 14
Qin, X., Sun, J., Liu, M., Zhang, L., Yin, Q., & Chen, S. E. (2023) · International Journal of Nursing Practice · doi:10.1111/ijn.13226 · Cited by 14
ÖZDEMİR, O., & Seçkin, H. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1349835 · Cited by 38
Arida, R. M., Passos, A. A., Graciani, A. L., Brogin, J. A. F., Ribeiro, M. D. A. L., Faber, J., Gutierre, R. C., & Teixeira-Machado, L. (2021) · Frontiers in Neurology · doi:10.3389/fneur.2021.771123 · Cited by 14
“(25), under the random-effects model the combined estimation is not an estimate of one fixed value, but rather the average of a distribution of values.”
BackgroundMa, S., Qu, G., Sun, C., Liu, H., Jiang, Y., Li, N., Wu, B., Gao, J., Feng, L., Xie, P., et al. (2022) · European Journal of Clinical Pharmacology · doi:10.1007/s00228-022-03414-y · Cited by 14
“In order to promote the results of our study beyond the included studies, random-effects model is the most appropriate meta-analysis model [31].”
ResultGroeneveld, N. S., Bijlsma, M. W., van de Beek, D., & Brouwer, M. C. (2024) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2024.12.009 · Cited by 17
Khalafi, M., Maleki, A. H., Mojtahedi, S., Ehsanifar, M., Rosenkranz, S. K., Symonds, M. E., Tarashi, M. S., Fatolahi, S., & Fernández, M. L. (2025) · Nutrients · doi:10.3390/nu17152388 · Cited by 15
“These models were selected because of the assumption that heterogeneity was likely in clinical trials [30].”
Fernandez, R. S., Ellwood, L., Barrett, D., & Weaver, J. C. (2020) · JBI Evidence Synthesis · doi:10.11124/jbisrir-d-19-00343 · Cited by 13
“The choice of model (random or fixed effects) and method for meta-analysis was based on the guidance by Tufanaru et al.(40) All pooled statistics were subject to double data entry.”
MethodThe role of gut microbiota on cognitive development in rodents: a meta-analysis
Putri, S. S. F., Irfannuddin, I., Murti, K., Kesuma, Y., Darmawan, H., & Koibuchi, N. (2023) · The Journal of Physiological Sciences · doi:10.1186/s12576-023-00869-1 · Cited by 13
“Otherwise, the fixedeffects model would be selected [24].”
MethodSercenia, J. C., & Prudente, M. S. (2023) · International Journal of Instruction · doi:10.29333/iji.2023.16432a · Cited by 13
Mulugeta, H., Sinclair, P. M., & Wilson, A. (2023) · Quality of Life Research · doi:10.1007/s11136-023-03563-2 · Cited by 13
Ahn, J., Song, J.-H., Shin, I., Cho, I. Y., & Kang, M. (2024) · Journal of Epidemiology & Community Health · doi:10.1136/jech-2023-220912 · Cited by 13
“12 In order to examine the effect of various factors, subgroup analyses were conducted, including subgroup analyses based on the unit of measurement for working hours (weekly, daily or monthly), long working hour definition, study design (cross-sectional or cohort), outcome measurement (self-report…”
Kazeminasab, F., Behzadnejad, N., Cerqueira, H. S. C., Santos, H. O., & Rosenkranz, S. K. (2024) · Frontiers in Nutrition · doi:10.3389/fnut.2024.1362731 · Cited by 17
Hou, M., Luo, X., He, S., Yang, X., Zhang, Q. H., Jin, M., Zhang, P., Li, Y., Bi, X., Li, J., et al. (2024) · The Journal of Headache and Pain · doi:10.1186/s10194-024-01822-2 · Cited by 13
“If not, the random-effect model is taken into account [22].”
MethodKazeminasab, F., Miraghajani, M. S., Mokhtari, K., Karimi, B., Rosenkranz, S. K., & Santos, H. O. (2024) · Nutrition & Metabolism · doi:10.1186/s12986-024-00826-8 · Cited by 15
“The results were combined using random-effects models due to the likelihood of heterogeneity arising from clinical or methodological factors that could potentially impact the outcomes [33].”
MethodNishi, S. K., Paz‐Graniel, I., Ni, J., Valle‐Hita, C., Khoury, N., García-Gavilán, J. F., Babió, N., & Salas‐Salvadó, J. (2024) · Nutrition Metabolism and Cardiovascular Diseases · doi:10.1016/j.numecd.2024.10.009 · Cited by 14
Koyu, H. Ö., & Törüner, E. K. (2025) · Psycho-Oncology · doi:10.1002/pon.70097 · Cited by 13
Fazekas, T., Miszczyk, M., Giesen, A., Kói, T., Zattoni, F., Rodríguez‐Sánchez, L., Yanagisawa, T., Matsukawa, A., Szarvas, T., Kryst, P., et al. (2025) · European Urology Focus · doi:10.1016/j.euf.2025.05.006 · Cited by 13
“Based on the likely heterogeneity of the studies, we utilized random-effect models [12].”
Mantovani, M. D. F., Kalinke, L. P., Mattei, Â. T., Arthur, J. P., Radovanovic, C. A. T., & Bortolato-Major, C. (2021) · Investigación y Educación en Enfermería · doi:10.17533/udea.iee.v39n1e04 · Cited by 13
“A critical evaluation of the studies was made and the results of interest were described using the instruments and tools from the Joanna Briggs Institute.”
MethodInfluentialMeng, C. F., Rajesh, D. A., Jannat‐Khah, D., Jivanelli, B., & Bykerk, V. P. (2022) · The Journal of Rheumatology · doi:10.3899/jrheum.220152 · Cited by 13
Meta-analysis of soluble tumour necrosis factor receptors in severe mental illnesses
Goh, X. X., Tang, P. Y., & Tee, S. F. (2023) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2023.07.014 · Cited by 14
Megaritis, D., Hume, E., Chynkiamis, N., Buckley, C., Polhemus, A. M., Watz, H., Troosters, T., & Vogiatzis, I. (2023) · ERJ Open Research · doi:10.1183/23120541.00409-2023 · Cited by 13
“A random effects model was used for the meta-analyses in order to allow generalisation inference [22].”
da Silva, R. C. G., Cardoso, D., & Apóstolo, J. (2016) · The JBI Database of Systematic Reviews and Implementation Reports · doi:10.11124/jbisrir-2016-2638 · Cited by 13
“Unauthorize studies are included in the meta-analysis, it will be performed using the fixed-effects model.(27) All results will be subject to double data entry.”
MethodAwareness and use of systematic literature reviews and meta‐analyses by ministerial policy analysts
Bédard, P., & Ouimet, M. (2017) · Canadian Public Administration · doi:10.1111/capa.12215 · Cited by 17
Dol, J., Richardson, B., Murphy, G. T., Aston, M. L., McMillan, D., & Campbell-Yeo, M. L. (2019) · The JBI Database of Systematic Reviews and Implementation Reports · doi:10.11124/jbisrir-d-19-00003 · Cited by 13
Song, Q., Liu, R., Yang, K., Tu, X., Tan, H., Fan, C., & Li, X. (2025) · Journal of the American Heart Association · doi:10.1161/jaha.125.041283 · Cited by 13
“20,21 While this approach is statistically appropriate under these conditions, it limits the generalizability of our findings, because the estimated effect reflects only the specific studies analyzed.”
InfluentialSOUZA, M. M. X. D., Al‐Sharif, L., Antunes, V., Wong, S. Y., Huang, D. Q., & Loomba, R. S. (2026) · Alimentary Pharmacology & Therapeutics · doi:10.1111/apt.70565 · Cited by 12
“In pairwise meta-analysis, the treatment effect was estimated as risk ratios (RRs) with their 95% confidence intervals (CIs) for each comparison using a random-effects model [31].”
Hall, R. L., George, E. S., Tierney, A. C., & Reddy, A. J. (2023) · Advances in Nutrition · doi:10.1016/j.advnut.2023.01.001 · Cited by 14
Wang, S., Zhang, X., Zhang, Q., Zhang, B., & Zhao, L. (2023) · BMJ Open Diabetes Research & Care · doi:10.1136/bmjdrc-2022-003198 · Cited by 14
Quek, J., Tan, D. J. H., Chan, K. E., Lim, W. H., Ng, C. H., Ren, Y. P., Koh, T. K., Teh, R., Xiao, J., Fu, C. E., et al. (2023) · Digestive Diseases · doi:10.1159/000531016 · Cited by 13
Qiu, Y., Yin, Z., Wang, M., Duan, A., Xie, M., Wu, J., Wang, Z., & Chen, G. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1212640 · Cited by 12
“We selected the random effect model for analysis when heterogeneity was >50%, otherwise, we selected the fixed effect model (Higgins et al., 2003; Tufanaru et al., 2015).”
MethodKebede, H. K., Gesesew, H. A., & Ward, P. (2023) · BMJ Open · doi:10.1136/bmjopen-2022-069308 · Cited by 12
Human papillomaviruses and breast cancer: A systematic review and meta‑analysis
Karachalios, C., Petousis, S., Margioula‐Siarkou, C., & Dinas, K. D. (2023) · Oncology Letters · doi:10.3892/ol.2023.14208 · Cited by 13
Chang-jiang, L., Dong, X., Jia, J., & Ha, M. (2024) · Biological Research For Nursing · doi:10.1177/10998004241227561 · Cited by 13
“I 2 25% represented very low heterogeneity, 25% I 2 50% indicated low heterogeneity, 50% I 2 75% reported moderate heterogeneity, and I 2 ≥ 75% explained substantial-high heterogeneity (Tufanaru et al., 2015).”
Ilola, T., Malmisalo, M., Laukka, E., Lehtiniemi, H., Pölkki, T., Kääriäinen, M., He, H. G., & Kanste, O. I. (2024) · Journal of research in nursing · doi:10.1177/17449871241226914 · Cited by 12
Gao, H., Chen, F., & Wang, S. (2024) · Phytotherapy Research · doi:10.1002/ptr.8231 · Cited by 12
Majage, S., Ravikumar, R. H., Prasanna, M., Chandramouli, M., Datta, P. K., & Baidya, D. K. (2024) · Indian Journal of Anaesthesia · doi:10.4103/ija.ija_373_24 · Cited by 12
“[14] I 2 was used to test the heterogeneity.”
MethodThe effectiveness of fibrin sealants in head and neck surgery: a systematic review and meta-analysis
Nguyen, M., Tran, L., Foreman, A., & Lockwood, C. S. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02634-w · Cited by 12
“Statistical analyses were performed using a fixed effect model [29].”
MethodKhalafi, M., Rosenkranz, S. K., Ghasemi, F., Kheradmand, S., Maleki, A. H., Korivi, M., & Tsao, J.-P. (2025) · Nutrition & Metabolism · doi:10.1186/s12986-024-00885-x · Cited by 16
“Random effects models were chosen due to assumed heterogeneity was likely from a clinical or methodologic perspective [64] and studies with greater potential for bias, such as uncontrolled or nonrandomized ones, show greater treatment effect as well as greater heterogeneity [65] which may have…”
Pascual‐Morena, C., Garrido‐Miguel, M., Martínez‐García, I., Lucerón‐Lucas‐Torres, M., Rodríguez‐Gutiérrez, E., Berlanga‐Macías, C., Fernández‐Bravo‐Rodrigo, J., & Patiño‐Cardona, S. (2025) · Nutrients · doi:10.3390/nu17101638 · Cited by 12
“When two or more studies estimated the association between dAGEs intake and cancer risk in the same way (i.e., overall or by specific cancer site) or mortality risk in the same way (i.e., overall or by specific cancer site), random-and fixed-effects meta-analyses were performed [17,22].”
Developing, Conducting, and Publishing Appropriate Systematic Review and Meta-Analysis Articles
Kelley, B., & Chung, K. C. (2017) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000004031 · Cited by 12
Wang, L., Pei, D., Ouyang, Y., & Nie, X. (2018) · International Journal of Nursing Practice · doi:10.1111/ijn.12707 · Cited by 12
Greenwood, J., Nygard, B., & Brickey, D. (2020) · JBI Evidence Synthesis · doi:10.11124/jbisrir-d-19-00414 · Cited by 12
“Statistical analyses were performed using the fixed effects model.(27) Where statistical pooling was not possible due to only one study reporting on a variable at a certain time point, the findings were presented in narrative form.”
MethodMeta-analysis in the production chain of aquaculture: A review
Yu, G., Liu, C., Zheng, Y., Chen, Y., Li, D., & Qin, W. (2021) · Information Processing in Agriculture · doi:10.1016/j.inpa.2021.04.002 · Cited by 12
Pascual‐Morena, C., Martínez‐Vizcaíno, V., Saz‐Lara, A., López‐Gil, J. F., Fernández‐Bravo‐Rodrigo, J., & Cavero‐Redondo, I. (2022) · Journal of Neurology · doi:10.1007/s00415-022-11040-y · Cited by 12
“A random effects meta-analysis [20, 21] was performed to determine the prevalence of epilepsy according to population subgroup (i.”
MethodInsomnia in patients treated with checkpoint inhibitors for cancer: A meta-analysis
Kišš, I., Kuhn, M., Hrušák, K., Buchler, B., Boublíková, L., & Büchler, T. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.946307 · Cited by 12
“The random effect model was used to compare pooled data (19).”
MethodJournal Club: High-dose methylprednisolone for acute traumatic spinal cord injury
Liu, L. J. W., Rösner, J., & Cragg, J. J. (2020) · Neurology · doi:10.1212/wnl.0000000000009263 · Cited by 12
“To account for these between-study differences (heterogeneity), randomeffects meta-analysis is used.(12) Heterogeneity was assessed with I(2) statistics, which describe the percentage of variation across studies that is due to heterogeneity rather than chance, and a 95% confidence interval (CI) can be constructed for…”
BackgroundMethodPestana‐Santos, M., Pereira, M. J. V. D. C. R., Santos, E. J. F., Lomba, L., & Santos, M. R. (2021) · JBI Evidence Synthesis · doi:10.11124/jbies-20-00359 · Cited by 13
“Statistical analyses will be performed using random effects models only in the presence of moderate to high heterogeneity (I(2)> 50%) and, in their absence, fixed effects models will be used instead.(29) Subgroup analyses will be conducted where there is sufficient data to investigate, based on the different study des…”
MethodTay, P. W. L., Ng, C. H., Lin, S. Y., Chin, Y. H., Xiao, J., Lim, W. H., Lim, S. Y., Fu, C. E., Chan, K. E., Quek, J., et al. (2022) · The American Journal of Gastroenterology · doi:10.14309/ajg.0000000000002042 · Cited by 12
“Random effects model was used in all analyses regardless of heterogeneity measures as evidence has demonstrated more robust effect estimateswith randomeffect compared tofixed effectmodels (27,28).”
MethodPatti, M., Christian, R., & Palokas, M. J. (2021) · JBI Evidence Synthesis · doi:10.11124/jbies-20-00043 · Cited by 11
“The choice of random effects model was based on the guidance by Tufanaru et al.30 Subgroup analyses were not conducted.”
MethodInfluentialAnalgesics for the management of acute dental pain in the pediatric population
Miroshnychenko, A., Azab, M., Ibrahim, S., Roldán, Y., Martinez, J. P. D., Tamilselvan, D., He, L., Urquhart, O., Tampi, M. P., Polk, D. E., et al. (2023) · The Journal of the American Dental Association · doi:10.1016/j.adaj.2023.02.013 · Cited by 12
“20”
Li, Y., Stern, N., Wang, P. Z. T., Braga, L. H., & Davé, S. (2023) · Journal of Pediatric Urology · doi:10.1016/j.jpurol.2023.08.033 · Cited by 11
Serra, R. D., de Oliveira, C. S., Roque, S., Herrera, F., & do Arco, H. M. D. S. L. R. (2023) · JBI Evidence Synthesis · doi:10.11124/jbies-23-00096 · Cited by 11
Vanhollebeke, G., Aers, F., Goethals, L., Raedt, R. D., Baeken, C., van Mierlo, P., & Vanderhasselt, M. (2023) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2023.105464 · Cited by 11
Wu, F., Wang, C., Li, S., Ye, Y., Cui, M., Liu, Y., Jiang, S., Qian, J., Yuan, J., Shu, Y., et al. (2024) · Viruses · doi:10.3390/v16020278 · Cited by 11
“According to the recommended synthetic calculation methods [30], if the included articles were less than five, we used the fixed effect model (also called the common effect model) to calculate pooled values regardless of the heterogeneity.”
MethodAcevedo, D., García, J. R., Grewal, R. S., Vankara, A., Murdock, C. J., Hardigan, P. C., & Aiyer, A. A. (2024) · Journal of Orthopaedics · doi:10.1016/j.jor.2024.02.034 · Cited by 11
Wen, S., Xuchen, Y. U., Lei, J. I. N., Junru, G. O. N. G., Zhang, X. D., Jinglin, S. U. N., Zhang, S., & Lyu, H. (2024) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2024.00771 · Cited by 12
Zhang, Y., Li, J., Li, X., Geng, Q., Xie, Y., Zhang, G., Wei, M., & Ma, Y. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02515-2 · Cited by 12
“A random-effects meta-analysis model was used to combine treatment rates [25].”
Method
Metadata
- Authors
- Tufanaru, C., Munn, Z., Stephenson, M., & Aromataris, E.
- Affiliations
- The University of Adelaide (AU)
- Venue
- International Journal of Evidence-Based Healthcare
- Published
- 2015-09
- Volume
- 13
- Issue
- 3
- Pages
- 196-207
- ISSN
- 1744-1595 (ISSN-L)
- 1744-1609
- OpenAlex
- W2180006680
- Cited by
- 1,057
- References
- 62
- Citations by year
- 2026: 77 · 2025: 151 · 2024: 204 · 2023: 167 · 2022: 157 · 2021: 101 · 2020: 65 · 2019: 57 · 2018: 48 · 2017: 22 · 2016: 8
- FWCI
- 4.28
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- International Journal of Evidence-Based Healthcare (publishedVersion)
- PubMed (publishedVersion)
- Adelaide Research & Scholarship (AR&S) (University of Adelaide) (submittedVersion)
- 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 › Sociology and Political Science › Delphi Technique in Research
- Keywords
- fixed-effects meta-analysis, random-effects meta-analysis, systematic review methodology, intervention effectiveness, effect size, research design
- MeSH terms
- Humans, Research Design, Review Literature as Topic, Meta-Analysis as Topic, Odds Ratio, Guidelines as Topic, Cross-Over Studies, Evidence-Based Medicine, Observational Studies as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
