基准剂量估计的非参数贝叶斯方法研究与应用

The Study and Application of Nonparametric Bayesian Methods for Benchmark Dose Estimation

目的比较两种基准剂量估计的非参数贝叶斯方法在不同剂量反应数据情形下的表现,再与参数模型作比较。方法介绍基于加权过程和随机过程的非参数贝叶斯方法的基本原理,通过模拟分析与实例研究比较各方法结果的差异。结果模拟研究显示,两种非参数方法 NPB1和NPB2的估计结果都与真实BMD值较为接近,NPB2方法的BMDL覆盖率更接近真实水平,因此更为可取;实例中与参数模型结果相比,非参数方法得到的BMD估计值都落入或非常接近由参数模型得到的BMD估计值的范围,而非参数方法估计的BMDLs值大多比参数模型算得的BMDLs值要小。结论两种非参数贝叶斯方法都可提供合理的拟合值,尤其是在传统的参数模型无法得到拟合结果的情况下,也可很好的应用;NPB2方法在估计结果和软件运算速度方面均略优于NPB1。

Objective Comparing the performance of the two nonparametric Bayesian methods for benchmark dose esti- mating under different dose response data, then comparing them with traditional parametric methods. Methods Introduce the basic principle of the nonparametric Bayesian method based on weighted process and stochastic process separately, then compared the estimations through simulate study and instance analysis. Results The simulate study shows that the posterior estimates were reasonably close to the target true BMD value for the two nonparametfic methods, and NBP2 is more desirable compared to NPB1. The nine examples indicate that the BMD estimates from the nonparametric approaches generally fall into or very near the interval of those obtained from BMDS and nonparametric approaches tend to produce lower BMDLs than the parametric model- ing approaches. Conclusion The posterior estimates were reasonably close to the target true BMD value for the two nonpara- metric methods, especially when standard parametric models fail to fit to the data adequately. The NPB2 method is slightly bet - ter than the NPB1 method in the aspect of estimation result and the software operation speed.