变换区域舍选法在贝塔分布随机数中的应用

Domain Transformation Acceptance-rejection Method and Its Application in Beta Variates

讨论了该方法在贝塔分布随机数中的应用,给出了尾部区间由变换区域舍选法而中心区间由Patchwork方法产生的贝塔分布随机数算法。实验结果显示,该算法的性能与贝塔分布随机数两种常用算法的性能非常接近。变换区域舍选法算法的主要优点在于尾部区间的抽样仅用到贝塔密度函数在尾部区间的凸性,而其他算法需要利用贝塔密度函数的特殊性质。

The authors discuss the application of domain transformation acceptance-rejection method in Beta; vatiates and give the Beta variates algorithm generated by domain transformation acceptance-rejection method in the tail intervals and Patchwork method in central intervals. The experimental results show that the performance of this method is very close to that of the two common algorithms of Beta variates. The main strong points of this method lie in the fact that the sampling in tail intervals only adopts the concave property of Beta density function in this interval, while other algorithms need to adopt the special characteristics of this function.