BayesPPDSurv is an R package designed for Bayesian analysis of survival data, enabling the incorporation of historical information into clinical trial designs. The package utilizes the piecewise constant hazard proportional hazards model, allowing researchers to tap into historical datasets to inform treatment effect parameters and covariates in survival analysis. A novel algorithm increases computational efficiency, supporting arbitrary sampling priors for determining Bayesian power and type I error rates. The efficacy of BayesPPDSurv is illustrated through a case study focused on melanoma clinical trials, demonstrating its practical applications in enhancing trial efficiency.
The BayesPPDSurv R package allows for Bayesian analysis of time-to-event outcomes by integrating historical data to inform treatment effects, enhancing clinical trial efficiency.
The package features a piecewise constant hazard proportional hazards model, utilizing historical data to improve predictive power and accuracy in survival analysis.
Collection
[
|
...
]