The Study and Application of Nonparametric Bayesian Methods for Benchmark Dose Estimation / 中国卫生统计

ABSTRACT

Objective Comparing the performance of the two nonparametric Bayesian methods for benchmark dose estimating 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 nonparametric 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 modeling approaches.Conclusion The posterior estimates were reasonably close to the target true BMD value for the two nonparametric 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.