论文标题
SPSURV：用于半参数生存分析的R包装
spsurv: An R package for semi-parametric survival analysis
论文作者
论文摘要
软件开发创新和计算的进步使医学研究（生存分析），工程研究（可靠性分析）和社会科学事件分析（历史分析）中的计算更加复杂且成本较低。结果，当涉及到事实数据分析时，出现了许多半参数建模工作。在这种情况下，这项工作介绍了基于伯恩斯坦多项式（BP）的灵活生存数据建模框架。这种创新的方法应用于现有模型家族，例如比例危害（pH），比例赔率（PO）和加速故障时间（AFT）模型，以估算未知的基线功能。除了这项贡献外，这项工作还利用Stan中可用的算法介绍了R中的新自动化例程。通过基于人工数据集的仿真研究对提出的计算例程进行了测试和探索。为拟合拟议的统计模型而实施的工具是通过R软件包组合和组织的。此外，基于BP的比例危害（BPPH），比例赔率（BPPO）和加速故障时间（BPAFT）模型在与癌症试验数据有关的实际应用中使用最大似然（ML）估计和Markov Chain Chain Monte Carlo（MCMC）方法进行了说明。
Software development innovations and advances in computing have enabled more complex and less costly computations in medical research (survival analysis), engineering studies (reliability analysis), and social sciences event analysis (historical analysis). As a result, many semi-parametric modeling efforts emerged when it comes to time-to-event data analysis. In this context, this work presents a flexible Bernstein polynomial (BP) based framework for survival data modeling. This innovative approach is applied to existing families of models such as proportional hazards (PH), proportional odds (PO), and accelerated failure time (AFT) models to estimate unknown baseline functions. Along with this contribution, this work also presents new automated routines in R, taking advantage of algorithms available in Stan. The proposed computation routines are tested and explored through simulation studies based on artificial datasets. The tools implemented to fit the proposed statistical models are combined and organized in an R package. Also, the BP based proportional hazards (BPPH), proportional odds (BPPO), and accelerated failure time (BPAFT) models are illustrated in real applications related to cancer trial data using maximum likelihood (ML) estimation and Markov chain Monte Carlo (MCMC) methods.
