Propensity scores are widely used in observational pharmacoepidemiology studies to control confounding bias and improve the reliability of causal effect estimation. The Guide on Methodological Standards in Pharmacoepidemiology (2nd edition) summarizes the basic concepts and application scenarios of propensity scores. Building upon this guideline, this paper elaborates on the key practical elements of propensity score analysis through examples, following a standardized workflow encompassing covariate selection, propensity score estimation, assessment of basic assumptions, propensity score application (matching, stratification, regression, or weighting), covariate balance test, causal effect estimation, sensitivity analysis, and standardized reporting. The aim is to provide a practical reference for clinical and epidemiological researchers in conducting standardized selection, implementation, and reporting of propensity score analysis in real-world studies on drug efficacy and safety.

1. 曾繁典, 郑荣远, 詹思延, 等主编. 药物流行病学, 第2版[M]. 北京: 中国医药科技出版社, 2016: 1-650.

2. 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.

3. 中国药学会. 中国药学会关于发布《药物流行病学研究方法学指南（第2版）》团体标准的公告[EB/OL]. (2025-11-03) [2026-03-16]. https://www.cpa.org.cn/index.php?do=info&cid=76925.

4. Rosenbaum PR, Rubin DB. The central role of the propensity score in observational studies for causal effects[J]. Biometrika, 1983, 70(1): 41-55. DOI: 10.1093/biomet/70.1.41.

5. Chen JW, Maldonado DR, Kowalski BL, et al. Best practice guidelines for propensity score methods in medical research: consideration on theory, implementation, and reporting. A review[J]. Arthroscopy, 2022, 38(2): 632-642. DOI: 10.1016/j.arthro.2021.06.037.

6. Jackson JW, Schmid I, Stuart EA. Propensity scores in pharmacoepidemiology: beyond the horizon[J]. Curr Epidemiol Rep, 2017, 4(4): 271-280. DOI: 10.1007/s40471-017-0131-y.

7. Saarela O, Stephens DA, Moodie EE. The role of exchangeability in causal inference[J]. Stat Sci, 2023, 38(3): 369-385. DOI: 10.1214/22-STS879.

8. Cole SR, Hernán MA. Constructing inverse probability weights for marginal structural models[J]. Am J Epidemiol, 2008, 168(6): 656-664. DOI: 10.1093/aje/kwn164.

9. Tennant PWG, Murray EJ, Arnold KF, et al. Use of directed acyclic graphs (DAGs) to identify confounders in applied health research: review and recommendations[J]. Int J Epidemiol, 2021, 50(2): 620-632. DOI: 10.1093/ije/dyaa213.

10. 韦柏安, 陈耿杭, 刘少南, 等. 有向无环图构建与应用步骤解读[J]. 中国循证医学杂志, 2025, 25(11): 1350-1357. [Wei BA, Chen GH, Liu SN, et al. Interpretation of the steps in the construction and application of directed acyclic graphs[J]. Chinese Journal of Evidence-Based Medicine, 2025, 25(11): 1350-1357.]. DOI: 10.7507/1672-2531.202506078.

11. Ding P, VanderWeele TJ, Robins JM. Instrumental variables as bias amplifiers with general outcome and confounding[J]. Biometrika, 2017, 104(2): 291-302. DOI: 10.1093/biomet/asx009.

12. Tönnies T, Kahl S, Kuss O. Collider bias in observational studies[J]. Dtsch Arztebl Int, 2022, 119(7): 107-122. DOI: 10.3238/arztebl.m2022.0076.

13. van Zwieten A, Tennant PWG, Kelly-Irving M, et al. Avoiding overadjustment bias in social epidemiology through appropriate covariate selection: a primer[J]. J Clin Epidemiol, 2022, 149: 127-136. DOI: 10.1016/j.jclinepi.2022.05.021.

14. VanderWeele T. Principles of confounder selection[J]. Eur J Epidemiol, 2019, 34(3): 211-219. DOI: 10.1007/s10654-019-00494-6.

15. Hoffman KL, Schenck EJ, Satlin MJ, et al. Comparison of a target trial emulation framework vs cox regression to estimate the association of corticosteroids with COVID-19 mortality[J]. JAMA Netw Open, 2022, 5(10): e2234425. DOI: 10.1001/jamanetworkopen.2022.34425.

16. Westreich D, Lessler J, Funk MJ. Propensity score estimation: neural networks, support vector machines, decision trees (CART), and Meta-classifiers as alternatives to Logistic regression[J]. J Clin Epidemiol, 2010, 63(8): 826-833. DOI: 10.1016/j.jclinepi. 2009.11.020.

17. 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.

18. Austin P. Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples[J]. Stat Med, 2009, 28(25): 3083-3107. DOI: 10.1002/sim.3697.

19. Stuart EA, Lee BK, Leacy FP. Prognostic score-based balance measures can be a useful diagnostic for propensity score methods in comparative effectiveness research[J]. J Clin Epidemiol, 2013, 66(8 Suppl): S84-S90.e1. DOI: 10.1016/j.jclinepi.2013.01.013.

20. Lee J, Little TD. A practical guide to propensity score analysis for applied clinical research[J]. Behav Res Ther, 2017, 98: 76-90. DOI: 10.1016/j.brat.2017.01.005.

21. Loke YK, Mattishent K. Propensity score methods in real-world epidemiology: a practical guide for first-time users[J]. Diabetes Obes Metab, 2020, 22 Suppl 3: 13-20. DOI: 10.1111/dom.13926.

22. Imbens GW. Nonparametric estimation of average treatment effects under exogeneity: a review[J]. Rev Econ Stat, 2004, 86(1): 4-29. DOI: 10.3386/t0294.

23. Matsouaka RA, Zhou Y. Causal inference in the absence of positivity: the role of overlap weights[J]. Biom J, 2024, 66(4): e2300156. DOI: 10.1002/bimj.202300156.

24. Greifer N, Stuart EA. Choosing the estimand when matching or weighting in observational studies[EB/OL]. (2021-06-19) [2026-02-28]. https://arxiv.org/abs/2106.10577v1.

25. Stuart EA. Matching methods for causal inference: a review and a look forward[J]. Stat Sci, 2010, 25(1): 1-21. DOI: 10.1214/09-sts313.

26. Rosenbaum PR, Rubin DB. Constructing a control group using multivariate matched sampling methods that incorporate the propensity score[J]. Am Stat, 1985, 39(1): 33-38. https://doi.org/10.2307/2683903.

27. Rosenbaum PR. Optimal matching for observational studies[J]. J Am Stat Assoc, 1989, 84(408): 1024-1032. https://doi.org/10.2307/2290079.

28. Austin PC. A comparison of 12 algorithms for matching on the propensity score[J]. Stat Med, 2014, 33(6): 1057-1069. DOI: 10.1002/sim.6004.

29. Stuart EA, Green KM. Using full matching to estimate causal effects in nonexperimental studies: examining the relationship between adolescent marijuana use and adult outcomes[J]. Dev Psychol, 2008, 44(2): 395-406. DOI: 10.1037/0012-1649.44.2.395.

30. Austin PC, Stuart EA. The performance of inverse probability of treatment weighting and full matching on the propensity score in the presence of model misspecification when estimating the effect of treatment on survival outcomes[J]. Stat Methods Med Res, 2017, 26(4): 1654-1670. DOI: 10.1177/0962280215584401.

31. Glimm E, Yau L. Exact matching as an alternative to propensity score matching[J/OL]. Stat Biopharm Res, 2025: 1-11. [2026-02-28]. DOI: 10.48550/arXiv.2503.02850.

32. King G, Nielsen R. Why propensity scores should not be used for matching[J]. Polit Anal, 2019, 27(4): 435-454. DOI: 10.1017/pan.2019.11.

33. Ramsey DJ, Makwana B, Dani SS, et al. GLP-1 receptor agonists and sight-threatening ophthalmic complications in patients with type 2 diabetes[J]. JAMA Netw Open, 2025, 8(8): e2526321. DOI: 10.1001/jamanetworkopen.2025.26321.

34. Austin PC. An introduction to propensity score methods for reducing the effects of confounding in observational studies[J]. Multivariate Behav Res, 2011, 46(3): 399-424. DOI: 10.1080/00273171.2011.568786.

35. Cochran WG. The effectiveness of adjustment by subclassification in removing bias in observational studies[J]. Biometrics, 1968, 24(2): 295-313. DOI: 10.2307/2528036.

36. Desai RJ, Rothman KJ, Bateman BT, et al. A propensity-score-based fine stratification approach for confounding adjustment when exposure is infrequent[J]. Epidemiology, 2017, 28(2): 249-257. DOI: 10.1097/ede.0000000000000595.

37. Elze MC, Gregson J, Baber U, et al. Comparison of propensity score methods and covariate adjustment: evaluation in 4 cardiovascular studies[J]. J Am Coll Cardiol, 2017, 69(3): 345-357. DOI: 10.1016/j.jacc.2016.10.060.

38. Schafer JL, Kang J. Average causal effects from nonrandomized studies: a practical guide and simulated example[J]. Psychol Methods, 2008, 13(4): 279-313. DOI: 10.1037/a0014268.

39. Desai RJ, Franklin JM. Alternative approaches for confounding adjustment in observational studies using weighting based on the propensity score: a primer for practitioners[J]. BMJ, 2019, 367: l5657. DOI: 10.1136/bmj.l5657.

40. Kurz CF, Krzywinski M, Altman N. Propensity score weighting[J]. Nat Methods, 2025, 22(4): 638-640. DOI: 10.1038/s41592-025-02629-y.

41. Austin PC, Stuart EA. Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies[J]. Stat Med, 2015, 34(28): 3661-3679. DOI: 10.1002/sim.6607.

42. Brookhart MA, Wyss R, Layton JB, et al. Propensity score methods for confounding control in nonexperimental research[J]. Circ Cardiovasc Qual Outcomes, 2013, 6(5): 604-611. DOI: 10.1161/circoutcomes.113.000359.

43. Yoshida K, Hernández-Díaz S, Solomon DH, et al. Matching weights to simultaneously compare three treatment groups: comparison to three-way matching[J]. Epidemiology, 2017, 28(3): 387-395. DOI: 10.1097/ede.0000000000000627.

44. Li F, Thomas LE, Li F. Addressing extreme propensity scores via the overlap weights[J]. Am J Epidemiol, 2019, 188(1): 250-257. DOI: 10.1093/aje/kwy201.

45. Li F. Propensity score weighting for causal inference with multi-valued treatments[EB/OL]. (2018-08-16) [2026-02-28]. https://arxiv.org/abs/1808.05339.

46. Xu KY, Hartz SM, Borodovsky JT, et al. Association between benzodiazepine use with or without opioid use and all-cause mortality in the United States, 1999-2015[J]. JAMA Netw Open, 2020, 3(12): e2028557. DOI: 10.1001/jamanetworkopen. 2020.28557.

47. Lunceford JK, Davidian M. Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study[J]. Stat Med, 2004, 23(19): 2937-2960. DOI: 10.1002/sim.1903.

48. Staffa SJ, Zurakowski D. Five steps to successfully implement and evaluate propensity score matching in clinical research studies[J]. Anesth Analg, 2018, 127(4): 1066-1073. DOI: 10.1213/ane.0000000000002787.

49. Nguyen TL, Collins GS, Spence J, et al. Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance[J]. BMC Med Res Methodol, 2017, 17(1): 78. DOI: 10.1186/s12874-017-0338-0.

50. VanderWeele TJ, Ding P. Sensitivity analysis in observational research: introducing the E-value[J]. Ann Intern Med, 2017, 167(4): 268-274. DOI: 10.7326/m16-2607.

51. Li L, Shen C, Wu AC, et al. Propensity score-based sensitivity analysis method for uncontrolled confounding[J]. Am J Epidemiol, 2011, 174(3): 345-353. DOI: 10.1093/aje/kwr096.

52. Andrew BY, Alan Brookhart M, Pearse R, et al. Propensity score methods in observational research: brief review and guide for authors[J]. Br J Anaesth, 2023, 131(5): 805-809. DOI: 10.1016/j.bja.2023.06.054.

53. Zhou Y, Matsouaka RA, Thomas L. Propensity score weighting under limited overlap and model misspecification[J]. Stat Methods Med Res, 2020, 29(12): 3721-3756. DOI: 10.1177/0962280220940334.

54. Chatelet F, Verillaud B, Chevret S. How to perform prespecified subgroup analyses when using propensity score methods in the case of imbalanced subgroups[J]. BMC Med Res Methodol, 2023, 23(1): 255. DOI: 10.1186/s12874-023-02071-8.

55. Karim ME. High-dimensional propensity score and its machine learning extensions in residual confounding control[J]. Am Stat, 2025, 79(1): 72-90. DOI: 10.1080/00031305.2024.2368794.

56. Funk MJ, Westreich D, Wiesen C, et al. Doubly robust estimation of causal effects[J]. Am J Epidemiol, 2011, 173(7): 761-767. DOI: 10.1093/aje/kwq439.

57. Leite W, Zhang H, Collier Z, et al. Machine learning for propensity score estimation: a systematic review and reporting guidelines[J/ OL]. Psychol Methods, 2025. [2026-02-28]. DOI: 10.1037/met0000789.