เปรียบเทียบวิธี

	การทดลองทางคลินิกระยะที่ II แบบจับคู่	การจับคู่คะแนนแนวโน้ม
สาขาวิชา	ระบาดวิทยา	สถิติการวิจัย
ตระกูล	Process / pipeline	Process / pipeline
ปีกำเนิด	1960s–1980s (formalized with Simon optimal designs, 1989)	1983
ผู้ริเริ่ม	Gehan (1961) for Phase II designs; matching frameworks adapted from case-control methodology	Paul Rosenbaum and Donald Rubin
ประเภท	Controlled clinical trial design	Method
แหล่งต้นตำรับ	Gehan, E. A. (1961). The determination of the number of patients required in a preliminary and a follow-up trial of a new chemotherapeutic agent. Journal of Chronic Diseases, 13(4), 346–353.	Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41–55.
ชื่อเรียกอื่น	matched Phase II trial, historically matched Phase II study, propensity-matched Phase II trial, externally controlled Phase II trial	PSM, propensity score weighting, covariate balance
ที่เกี่ยวข้อง	5	3
สรุป	A matched Phase II clinical trial is a single-arm or small-controlled early-efficacy study in which treated patients are paired with matched controls — drawn from historical databases, registries, or concurrent external cohorts — on key prognostic variables such as age, disease stage, and performance status. This design allows preliminary efficacy assessment without a concurrent randomized arm, trading randomization for feasibility while partially controlling for confounding through the matching process.	Propensity score matching (PSM) is a method for reducing confounding bias in observational studies by balancing baseline characteristics between treatment groups, simulating randomization. Developed by Rosenbaum and Rubin (1983), it estimates the probability of receiving treatment given observed covariates, then matches or weights treated and control individuals with similar treatment probabilities. Widely used in medicine, epidemiology, and policy evaluation when randomized trials are infeasible or unethical, enabling estimation of treatment effects while controlling for selection bias.