The establishment of standardized statistical analysis strategies is of great significance to ensuring scientific value and promoting high-quality development in pharmacoepidemiology research. Based on the Guide on Methodological Standards in Pharmacoepidemiology (2nd edition), this article interprets the statistical analysis content within it section of the Guidelines. The first part outlines the importance and specific content of statistical analysis strategies in pharmacoepidemiology studies, introduces the variable definitions and sample size estimation and elaborates on data preprocessing and statistical methods. It also briefly discusses bias control and sensitivity analysis. The second part focuses on considerations for developing statistical analysis strategies, with further clarification on subgroup analysis, interim analysis, and the preparation of the statistical analysis reports.

1.The European Network of Centres for Pharmacoepidemiology and Pharmacovigilance (ENCePP). Guide on Methodological Standards in Pharmacoepidemiology (revision 11) [EB/OL]. (2023-07-13) [2025-06-04]. https://encepp.europa.eu/encepp-toolkit/methodological-guide_en.

2.International Society of Pharmacoepidemiology. Guidelines for good pharmacoepidemiology practice (GPP)[J]. Pharmacoepidemiol Drug Saf, 2016, 25(1): 2-10. DOI: 10.1002/pds.3891.

3.European Medicines Agency. Guideline on Good Pharmacovigilance Practices (GVP) Module VIII-Post-Authorisation Safety Studies (Rev 3) [EB/OL]. (2017-12-10) [2025-06-04]. https://www.ema.europa.eu/en/documents/scientific-guideline/guideline-good-pharmacovigilance-practices-gvp-module-viii-post-authorisation-safety-studies-rev-3_en.pdf.

4.胥洋, 丁呈怡, 詹思延. 中国药物流行病学研究方法学指南[J]. 药物流行病学杂志, 2019, 28(1): 5-9. [Xu Y, Ding CY, Zhan SY. Guide on Methodological Standards in Pharmacoepidemiology[J]. Chinese Journal of Pharmacoepidemiology, 2019, 28(1): 5-9.] DOI: 10.19960/j.cnki.issn1005-0698.2019.01.002.

5.颜济南, 吴昀效, 聂晓璐, 等. 《中国药物流行病学研究方法学指南（第2版）》的制订/修订过程[J]. 药物流行病学杂志, 2025, 34(2): 121-35. [Yan JN, Wu YX, Nie XL, et al. Revision process of the Guide on Methodological Standards in Pharmacoepidemiology in China (2nd edition)[J]. Chinese Journal of Pharmacoepidemiology, 2025, 34(2): 121-135.] DOI: 10.12173/j.issn.1005-0698.202502028.

6.Peduzzi P, Concato J, Kemper E, et al. A simulation study of the number of events per variable in logistic regression analysis[J]. J Clin Epidemiol, 1996, 49(12): 1373-1379. DOI: 10.1016/s0895-4356(96)00236-3.

7.Riley RD, Ensor J, Snell KIE, et al. Calculating the sample size required for developing a clinical prediction model[J]. BMJ, 2020, 368: m441. DOI: 10.1136/bmj.m441.

8.European Medicines Agency. ICH E9 statistical principles for clinical trials[EB/OL]. (1998-09-01) [2025-06-13]. https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e-9-statistical-principles-clinical-trials-step-5_en.pdf.

9.Heymans MW, Twisk JWR. Handling missing data in clinical research[J]. J Clin Epidemiol, 2022, 151: 185-188. DOI: 10.1016/j.jclinepi.2022.08.016.

10.Rigopoulos D, Tampouratzi E, Angelakopoulos C, et al. Real-world data on the effectiveness of brodalumab in patients with moderate-to severe plaque psoriasis in the Greek clinical setting (the BrIDGE study)[J]. J Eur Acad Dermatol Venereol, 2024, 38(6): 1121-1130. DOI: 10.1111/jdv.19816.

11.朱荣慧, 许金芳, 王睿, 等. 多重填补技术在医学研究缺失值处理中的应用及发展[J]. 中国卫生统计, 2022, 39(2): 293-295, 298. [Zhu RH, Xu JF, Wang R, et al. Application and development of multiple imputation in handling missing values in medical research[J]. Chinese Journal of Health Statistics, 2022, 39(2): 293-295, 298.] DOI: 10.3969/j.issn.1002-3674.202202034.

12.Vetter C, Devore EE, Wegrzyn LR, et al. Association between rotating night shift work and risk of coronary heart disease among women[J]. JAMA, 2016, 315(16): 1726-1734. DOI: 10.1001/jama.2016.4454.

13.黎剑锋, 张静怡, 李立康, 等. 临床试验中缺失值的处理方法探讨[J]. 协和医学杂志, 2024, 15(5): 1165-1172. [Li JF, Zhang JY, Li LK, et al. Approach to handling missing data in clinical trials[J]. Medical Journal of Peking Union Medical College Hospital, 2024, 15(5): 1165-1172.] DOI: 10.12290/xhyxzz.2023-0415.

14.Mongin D, Lauper K, Finckh A, et al. Accounting for missing data caused by drug cessation in observational comparative effectiveness research: a simulation study[J]. Ann Rheum Dis, 2022, 81(5): 729-736. DOI: 10.1136/annrheumdis-2021-221477.

15.Lee KJ, Tilling KM, Cornish RP, et al. Framework for the treatment and reporting of missing data in observational studies: the treatment and reporting of missing data in observational studies framework[J]. J Clin Epidemiol, 2021, 134: 79-88. DOI: 10.1016/j.jclinepi.2021.01.008.

16.韦连慧, 郭晓晶, 许金芳, 等. 缺失数据处理在药物流行病学研究中的应用及进展[J]. 药物流行病学杂志, 2022, 31(1): 60-64. [Wei LH, Guo XJ, Xu JF, et al. Application and progress of missing data handling methodology in pharmacoepidemiology[J]. Chinese Journal of Pharmacoepidemiology, 2022, 31(1): 60-64.]DOI: 10.19960/j.cnki.issn1005-0698.2022.01.009.

17.Madley-dowd P, Hughes R, Tilling K, et al. The proportion of missing data should not be used to guide decisions on multiple imputation[J]. J Clin Epidemiol, 2019, 110: 63-73. DOI: 10.1016/j.jclinepi.2019.02.016.

18.Gini R, Sturkenboom MCJ, Sultana J, et al. Different strategies to execute multi-database studies for medicines surveillance in real-world setting: a reflection on the European model[J]. Clin Pharmacol Ther, 2020, 108(2): 228-235. DOI: 10.1002/cpt.1833.

19.Dedman D, Cabecinha M, Williams R, et al. Approaches for combining primary care electronic health record data from multiple sources: a systematic review of observational studies[J]. BMJ Open, 2020, 10(10): e037405. DOI: 10.1136/bmjopen-2020-037405.

20.Gedeborg R, Igl W, Svennblad B, et al. Federated analyses of multiple data sources in drug safety studies[J]. Pharmacoepidemiol Drug Saf, 2023, 32(3): 279-286. DOI: 10.1002/pds.5587.

21.Hall GC, Sauer B, Bourke A, et al. Guidelines for good database selection and use in pharmacoepidemiology research[J]. Pharmacoepidemiol Drug Saf, 2012, 21(1): 1-10. DOI: 10.1002/pds.2229.

22.曾慧娴, 杨之雨, 柳东红, 等. 医学研究中常见统计分析方法的应用[J]. 上海预防医学, 2023, 35(8): 831-839. [Zeng HX, Yang ZY, Liu DH, et al. Selection and application of statistical methods in medical research[J]. Shanghai Journal of Preventive Medicine, 2023, 35(8): 831-839.] DOI: 10.19428/j.cnki.sjpm.2023.22771.

23.汤宁, 宋秋月, 易东, 等. 医学纵向数据建模方法及其统计分析策略[J]. 中国卫生统计, 2019, 36(3): 441-444, 447. [Tang N, Song QY, Yi D, et al. Modeling methods and statistical analysis strategies for medical longitudinal data[J]. Chinese Journal of Health Statistics, 2019, 36(3): 441-444, 447.] https://d.wanfangdata.com.cn/periodical/ChVQZXJpb2RpY2FsQ0hJMjAyNTA2MjISD3pnd3N0ajIwMTkwMzAzNhoIZjR1cnJ2ang%3D.

24.Jeong E, Su Y, Li L, et al. Discovering severe adverse reactions from pharmacokinetic drug-drug interactions through literature analysis and electronic health record verification[J]. Clin Pharmacol Ther, 2025, 117(4): 1078-1087. DOI: 10.1002/cpt.3500.

25.Yang Z, DehmeR M, Yli-harja O, et al. Combining deep learning with token selection for patient phenotyping from electronic health records[J]. Sci Rep, 2020, 10(1): 1432. DOI: 10.1038/s41598-020-58178-1.

26.Matheny ME, Yang J, Smith JC, et al. Enhancing postmarketing surveillance of medical products with large language models[J]. JAMA Netw Open, 2024, 7(8): e2428276. DOI: 10.1001/jamanetworkopen.2024.28276.

27.Cannas M, Arpino B. A comparison of machine learning algorithms and covariate balance measures for propensity score matching and weighting[J]. Biom J, 2019, 61(4): 1049-1072. DOI: 10.1002/bimj.201800132.

28.Yang C, Kors JA, Ioannou S, et al. Trends in the conduct and reporting of clinical prediction model development and validation: a systematic review[J]. J Am Med Inform Assoc, 2022, 29(5): 983-989. DOI: 10.1093/jamia/ocac002.

29.Yamamoto H, Kayanuma G, Nagashima T, et al. Early detection of adverse drug reaction signals by association rule mining using large-scale administrative claims data[J]. Drug Saf, 2023, 46(4): 371-389. DOI: 10.1007/s40264-023-01278-4.

30.Pfaff ER, Girvin AT, Bennett TD, et al. Identifying who has long COVID in the USA: a machine learning approach using N3C data[J]. Lancet Digit Health, 2022, 4(7): e532-e541. DOI: 10.1016/s2589-7500(22)00048-6.

31.Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods[J]. BMJ, 2024, 385: e078378. DOI: 10.1136/bmj-2023-078378.

32.van Royen FS, Asselbergs FW, Alfonso F, et al. Five critical quality criteria for artificial intelligence-based prediction models[J]. Eur Heart J, 2023, 44(46): 4831-4834. DOI: 10.1093/eurheartj/ehad727.

33.Chen L, Shi B, Feng S. Where medical statistics meets artificial intelligence[J]. N Engl J Med, 2023, 389(25): 2403. DOI: 10.1056/NEJMc2312332.

34.Lei J, Zhai J, Zhang Y, et al. Supervised machine learning models for predicting sepsis-associated liver injury in patients with sepsis: development and validation study based on a multicenter cohort study[J]. J Med Internet Res, 2025, 27: e66733. DOI: 10.2196/66733.

35.Ali S, Akhlaq F, Imran AS, et al. The enlightening role of explainable artificial intelligence in medical & healthcare domains: a systematic literature review[J]. Comput Biol Med, 2023, 166: 107555. DOI: 10.1016/j.compbiomed.2023.107555.

36.中国卫生信息与健康医疗大数据学会重症医学分会, 北京肿瘤学会重症医学专业委员会. 重症大数据应用中国专家共识（2022）[J]. 中华医学杂志, 2023, 103(6): 404-424. DOI: 10.3760/cma.j.cn112137-20221008-02098.

37.邓思危, 赵厚宇, 詹思延. 基于概况性综述的药物流行病学研究中时间相关性偏倚识别流程[J]. 中华流行病学杂志, 2024, 45(9): 1273-1282. [Deng SW, Zhao HY, Zhan SY, et al. Identification process of time-related bias in pharmacoepidemiologic research based on a scoping review[J]. Chinese Journal of Epidemiology, 2024, 45(9): 1273-1282.] DOI: 10.3760/cma.j.cn112338-20240123-00037.

38.Suissa S, Dell'aniello S. Time-related biases in pharmacoepidemiology[J]. Pharmacoepidemiol Drug Saf, 2020, 29(9): 1101-1110. DOI: 10.1002/pds.5083.

39.Hernán MA, Sauer BC, Hernández-díaz S, et al. Specifying a target trial prevents immortal time bias and other self-inflicted injuries in observational analyses[J]. J Clin Epidemiol, 2016, 79: 70-75. DOI: 10.1016/j.jclinepi.2016.04.014.

40.Suissa S. Immortal time bias in pharmaco-epidemiology[J]. Am J Epidemiol, 2008, 167(4): 492-499. DOI: 10.1093/aje/kwm324.

41.Suissa S, Dell'aniello S, Vahey S, et al. Time-window bias in case-control studies: statins and lung cancer[J]. Epidemiology, 2011, 22(2): 228-231. DOI: 10.1097/EDE.0b013e3182093a0f.

42.Lieslehto J, Tiihonen J, Lähteenvuo M, et al. Comparative effectiveness of pharmacotherapies for the risk of attempted or completed suicide among persons with borderline personality disorder[J]. JAMA Netw Open, 2023, 6(6): e2317130. DOI: 10.1001/jamanetworkopen.2023.17130.

43.许璐, 赵厚宇, 詹思延. 药物流行病学研究中的时间窗偏倚 [J]. 药物流行病学杂志, 2019, 28(12): 828-32. [Xu L, Zhao HY, Zhan SY. Time-window bias in pharmacoepidemiology Study [J]. Chinese Journal of Pharmacoepidemiology, 2019, 28(12): 828-832.] DOI: 10.19960/j.cnki.issn1005-0698.2019.12.010.

44.Klungel OH, Martens EP, Psaty BM, et al. Methods to assess intended effects of drug treatment in observational studies are reviewed[J]. J Clin Epidemiol, 2004, 57(12): 1223-1231. DOI: 10.1016/j.jclinepi.2004.03.011.

45.Robins JM, Hernán MA, Brumback B. Marginal structural models and causal inference in epidemiology[J]. Epidemiology, 2000, 11(5): 550-560. DOI: 10.1097/00001648-200009000-00011.

46.黄丽红, 魏永越, 陈峰. 如何控制观察性疗效比较研究中的混杂因素: （一）已测量混杂因素的统计学分析方法 [J]. 中华流行病学杂志, 2019, 40(10): 1304-1309. [Huang LH, Wei YY, Chen F. Confounder adjustment in observational comparative effectiveness researches: (1) statistical adjustment approaches for measured confounder[J]. Chinese Journal of Epidemiology, 2019, 40(10): 1304-1309.] DOI: 10.3760/cma.j.issn.0254-6450.2019.10.024.

47.Sabaté M, Montané E. Pharmacoepidemiology: an overview[J]. J Clin Med, 2023, 12(22): 7033. DOI: 10.3390/jcm12227033.

48.Uddin MJ, Groenwold RH, van Staa TP, et al. Performance of prior event rate ratio adjustment method in pharmacoepidemiology: a simulation study[J]. Pharmacoepidemiol Drug Saf, 2015, 24(5): 468-477. DOI: 10.1002/pds.3724.

49.European Medicines Agency. ICH E9 (R1) addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials[EB/OL]. (2020-07-30) [2025-06-13]. https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e9-r1-addendum-estimands-and-sensitivity-analysis-clinical-trials-guideline-statistical-principles-clinical-trials-step-5_en.pdf.

50.Cheng DM, Hogan JW. The sense and sensibility of sensitivity analyses[J]. N Engl J Med, 2024, 391(11): 972-974. DOI: 10.1056/NEJMp2403318.

51.国家药品监督管理局药物审评中心. 药物临床试验亚组分析指导原则[EB/OL]. (2020-12-31) [2025-06-13]. https://www.cqn.com.cn/ms/att/2021-02/09/f8fcb4fa-a5c3-4a47-9e16-3ce3a7b4f7ca.pdf.

52.Delgado-Herrera L, Anbar D. A model for the interim analysis process: a case study[J]. Control Clin Trials, 2003, 24(1): 51-65. DOI: 10.1016/s0197-2456(02)00275-1.

53.Walter SD, Han H, Guyatt GH, et al. A systematic survey of randomised trials that stopped early for reasons of futility[J]. BMC Med Res Methodol, 2020, 20(1): 10. DOI: 10.1186/s12874-020-0899-1.

54.郭洋, 蒋志伟, 夏结来, 等. 肿瘤药物临床试验中成组序贯设计的统计学考虑[J]. 中国临床药理学与治疗学, 2013, 18(2): 175-180. [Guo Y, Jiang ZW, Xia JL, et al. Statistical considerations of group sequential designs in oncology drug clinical trials[J]. Chinese Journal of Clinical Pharmacology and Therapeutics, 2013, 18(2): 175-180.] https://kns.cnki.net/kcms2/article/abstract?v=ZscdH8NaPi8y1GIKMfij9MwC7XO8STdcOmO6ANRJkrEly8dyKhBY8Him__damh7TLSFTLqylwJGTicq_ZxPmxPJGm2MrMcNwD-xCY7T1feKLlkBI4ACrxed8gS3uEEBzA_KXu5gQiaUty-p0fCZRPqwG0ZSj8GjGzw2SUnVs5CEHhPhQ30TM7Q==&uniplatform=NZKPT&language=CHS.

55.黄丽红. 临床试验期中分析中的两个统计学问题[D]. 南京: 南京医科大学, 2017.