方法对比

	贝叶斯Kaplan-Meier分析	贝叶斯Cox比例风险模型
领域	流行病学	流行病学
方法族	Process / pipeline	Process / pipeline
起源年份	1976	1972 (Cox); Bayesian formulation developed through the 1990s
提出者	Susarla & Van Ryzin (Bayesian nonparametric survival estimation)	D. R. Cox (frequentist CPH, 1972); Bayesian extensions by Joseph Ibrahim, Ming-Hui Chen, Debajyoti Sinha (1990s–2001)
类型	Bayesian nonparametric survival analysis	Bayesian semiparametric survival regression
开创性文献	Susarla, V., & Van Ryzin, J. (1976). Nonparametric Bayesian estimation of survival curves from incomplete observations. Journal of the American Statistical Association, 71(356), 897–902.	Ibrahim, J. G., Chen, M.-H., & Sinha, D. (2001). Bayesian Survival Analysis. Springer. ISBN: 978-0387952772
别名	Bayesian survival curve estimation, Bayesian nonparametric survival analysis, Dirichlet process Kaplan-Meier, BKM	Bayesian CPH, Bayesian survival regression, Bayesian semiparametric hazard model, Bayesian partial likelihood survival model
相关	4	4
摘要	Bayesian Kaplan-Meier analysis extends the classical Kaplan-Meier estimator by placing a prior distribution over the survival function and updating it with observed time-to-event data to obtain a full posterior distribution for the survival curve. This approach, rooted in Susarla and Van Ryzin's 1976 Dirichlet-process framework, yields credible intervals rather than confidence intervals and enables coherent incorporation of prior clinical knowledge, making it particularly valuable in small-sample or early-phase clinical settings.	The Bayesian Cox proportional hazards model combines Cox's classical semiparametric survival regression with Bayesian inference, replacing point estimates and p-values with full posterior distributions over regression coefficients. It handles right-censored time-to-event outcomes, quantifies uncertainty about hazard ratios in probabilistic terms, and allows the incorporation of prior clinical or historical knowledge directly into the analysis.