Evaluation of statistical performance for rare-event meta-analysis_Chinese Journal of Evidence-Based Medicine

Authors：

YAO Minghong ^1,2 , LI Ling ^1,2 , REN Yan ^1,2 , JIA Yulong ^1,2 , ZOU Kang ^1,2 ,  SUN Xin ^1,2

1. Chinese Evidence-based Medicine Center, West China Hospital, Sichuan University, Chengdu 610041, P.R.China;
2. Real World Data Research and Innovation Center of Boao Lecheng, Qionghai 571435, P.R.China;

Corresponding author：

SUN Xin, Email: sunx79@hotmail.com

Keywords：

Meta-analysis; Rare event; Zero event; Bayesian logistic regression model

DOI：

10.7507/1672-2531.202011055

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To examine statistical performance of different rare-event meta-analyses methods.Methods Using Monte-Carlo simulation, we set a variety of scenarios to evaluate the performance of various rare-event meta-analysis methods. The performance measures included absolute percentage error, root mean square error and interval coverage.Results Across different scenarios, the absolute percentage error and root mean square error were similar for Bayesian logistic regression model, generalized mixed linear effects model and continuity correction, but the interval coverage was higher with Bayesian logistic regression model. The statistical performances with Mantel-Haenszel method and Peto method were consistently suboptimal across different scenarios.Conclusions Bayesian logistic regression model may be recommended as a preferred approach for rare-event meta-analysis.

Citation： YAO Minghong, LI Ling, REN Yan, JIA Yulong, ZOU Kang, SUN Xin. Evaluation of statistical performance for rare-event meta-analysis. Chinese Journal of Evidence-Based Medicine, 2021, 21(3): 367-372. doi: 10.7507/1672-2531.202011055 Copy

1.	刘曼, 陈文松, 刘玉秀, 等. 单组率研究含零事件的Meta分析方法. 中国循证医学杂志, 2020, 20(10): 1226-1233.
2.	Mansournia MA, Geroldinger A, Greenland S, et al. Separation in logistic regression: causes, consequences, and control. Am J Epidemiol, 2018, 187(4): 864-870.
3.	Cummings P. The relative merits of risk ratios and odds ratios. Arch Pediatr Adolesc Med, 2009, 163(5): 438-445.
4.	Stijnen T, Hamza TH, Ozdemir P. Random effects meta-analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data. Stat Med, 2010, 29(29): 3046-3067.
5.	Bartlett MS. The continuity correction in 2×2 tables. Biometrika, 1964, 51(3-4): 327-337.
6.	Yusuf S, Peto R, Lewis J, et al. Beta blockade during and after myocardial infarction: an overview of the randomized trials. Prog Cardiovasc Dis, 1985, 27(5): 335-371.
7.	Robins J, Breslow N, Greenland S. Estimators of the Mantel-Haenszel variance consistent in both sparse data and large-strata limiting models. Biometrics, 1986, 42(2): 311-323.
8.	Burke DL, Ensor J, Riley RD. Meta-analysis using individual participant data: one-stage and two-stage approaches, and why they may differ. Stat Med, 2017, 36(5): 855-875.
9.	Cai T, Parast L, Ryan L. Meta-analysis for rare events. Stat Med, 2010, 29(20): 2078-2089.
10.	Günhan BK, Röver C, Friede T. Random-effects meta-analysis of few studies involving rare events. Res Synth Methods, 2020, 11(1): 74-90.
11.	Xu C, Li L, Lin L, et al. Exclusion of studies with no events in both arms in meta-analysis impacted the conclusions. J Clin Epidemiol, 2020, 123: 91-99.
12.	Cheng J, Pullenayegum E, Marshall JK, et al. Impact of including or excluding both-armed zero-event studies on using standard meta-analysis methods for rare event outcome: a simulation study. BMJ Open, 2016, 6(8): e010983.
13.	Jackson D, Law M, Stijnen T, et al. A comparison of seven random-effects models for meta-analyses that estimate the summary odds ratio. Stat Med, 2018, 37(7): 1059-1085.
14.	Kuss O. Statistical methods for meta-analyses including information from studies without any events-add nothing to nothing and succeed nevertheless. Stat Med, 2015, 34(7): 1097-1116.
15.	Friedrich JO, Adhikari NKJ, Beyene J. Inclusion of zero total event trials in meta-analyses maintains analytic consistency and incorporates all available data. BMC Med Res Method, 2007, 7(1): 5.
16.	Zhou Y, Zhu B, Lin L, et al. Protocols for meta-analysis of intervention safety seldom specified methods to deal with rare events. J Clin Epidemiol, 2020, 128: 109-117.
17.	Bradburn MJ, Deeks JJ, Berlin JA, et al. Much ado about nothing: a comparison of the performance of meta-analytical methods with rare events. Stat Med, 2007, 26(1): 53-77.
18.	Sweeting MJ, Sutton AJ, Lambert PC. What to add to nothing? Use and avoidance of continuity corrections in meta-analysis of sparse data. Stat Med, 2004, 23(9): 1351-1375.

1. 刘曼, 陈文松, 刘玉秀, 等. 单组率研究含零事件的Meta分析方法. 中国循证医学杂志, 2020, 20(10): 1226-1233.
2. Mansournia MA, Geroldinger A, Greenland S, et al. Separation in logistic regression: causes, consequences, and control. Am J Epidemiol, 2018, 187(4): 864-870.
3. Cummings P. The relative merits of risk ratios and odds ratios. Arch Pediatr Adolesc Med, 2009, 163(5): 438-445.
4. Stijnen T, Hamza TH, Ozdemir P. Random effects meta-analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data. Stat Med, 2010, 29(29): 3046-3067.
5. Bartlett MS. The continuity correction in 2×2 tables. Biometrika, 1964, 51(3-4): 327-337.
6. Yusuf S, Peto R, Lewis J, et al. Beta blockade during and after myocardial infarction: an overview of the randomized trials. Prog Cardiovasc Dis, 1985, 27(5): 335-371.
7. Robins J, Breslow N, Greenland S. Estimators of the Mantel-Haenszel variance consistent in both sparse data and large-strata limiting models. Biometrics, 1986, 42(2): 311-323.
8. Burke DL, Ensor J, Riley RD. Meta-analysis using individual participant data: one-stage and two-stage approaches, and why they may differ. Stat Med, 2017, 36(5): 855-875.
9. Cai T, Parast L, Ryan L. Meta-analysis for rare events. Stat Med, 2010, 29(20): 2078-2089.
10. Günhan BK, Röver C, Friede T. Random-effects meta-analysis of few studies involving rare events. Res Synth Methods, 2020, 11(1): 74-90.
11. Xu C, Li L, Lin L, et al. Exclusion of studies with no events in both arms in meta-analysis impacted the conclusions. J Clin Epidemiol, 2020, 123: 91-99.
12. Cheng J, Pullenayegum E, Marshall JK, et al. Impact of including or excluding both-armed zero-event studies on using standard meta-analysis methods for rare event outcome: a simulation study. BMJ Open, 2016, 6(8): e010983.
13. Jackson D, Law M, Stijnen T, et al. A comparison of seven random-effects models for meta-analyses that estimate the summary odds ratio. Stat Med, 2018, 37(7): 1059-1085.
14. Kuss O. Statistical methods for meta-analyses including information from studies without any events-add nothing to nothing and succeed nevertheless. Stat Med, 2015, 34(7): 1097-1116.
15. Friedrich JO, Adhikari NKJ, Beyene J. Inclusion of zero total event trials in meta-analyses maintains analytic consistency and incorporates all available data. BMC Med Res Method, 2007, 7(1): 5.
16. Zhou Y, Zhu B, Lin L, et al. Protocols for meta-analysis of intervention safety seldom specified methods to deal with rare events. J Clin Epidemiol, 2020, 128: 109-117.
17. Bradburn MJ, Deeks JJ, Berlin JA, et al. Much ado about nothing: a comparison of the performance of meta-analytical methods with rare events. Stat Med, 2007, 26(1): 53-77.
18. Sweeting MJ, Sutton AJ, Lambert PC. What to add to nothing? Use and avoidance of continuity corrections in meta-analysis of sparse data. Stat Med, 2004, 23(9): 1351-1375.

Previous Article
The sample size calculation for artificial intelligence diagnosis of contrast-enhanced ultrasound based on sensitivity and specificity

Chinese Journal of Evidence-Based Medicine

Evaluation of statistical performance for rare-event meta-analysis

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content