Randomized quasi-random sampling/importance resampling

Randomized quasi-random sampling/importance resampling
复制标题

随机准随机采样/重要性重采样

DOI:
10.1080/03610918.2018.1547398
复制
发表时间:
2018-12
期刊:
Communications in Statistics - Simulation and Computation
影响因子:
--
通讯作者:
Ning Jianhui
Ning Jianhui
中科院分区:
其他
文献类型:
--
作者:
Tao Huiqiang;Ning Jianhui

文献摘要

参考文献

被引文献

相似文献

摘要抽样/重要性重抽样方法是贝叶斯统计中广泛使用的方法。为了提高计算的扩展性和准确性,文献进行了各种改进。在这项工作中,进一步改进了基于准随机抽样/重要性重抽样的方法。提出了一种随机化的准随机采样/重要性重采样算法,并通过三个算例验证了该算法的性能。实证研究表明,该方法比抽样/重要性重采样法和准随机抽样/重要性重采样法具有更高的精度。此外,它还可以用来估计蒙特卡罗误差,而准随机抽样/重要性重抽样方法在这个问题上有约束。
Abstract Sampling/importance resampling method is widely used in Bayesian statistics. Literatures have carried out a variety of improvements to promote the computational expanse and the accuracy. In this work, further improvement based on quasi-random sampling/importance resampling method is derived. The randomized version of quasi-random sampling/importance resampling algorithm is proposed, and the performance is illustrated through three examples. The empirical study shows that the proposed approaches are more accurate than sampling/importance resampling method and quasi-random sampling/importance resampling method. Moreover, it can be used to estimate the Monte Carlo error, while the quasi-random sampling/importance resampling method has constraints in this problem.
DOI: 10.1198/tas.2003.s212
发表时间: 2003-02
期刊: The American Statistician
影响因子: --
作者:
R. D. Cook;S. Weisberg
通讯作者: R. D. Cook;S. Weisberg
DOI: 10.1006/jmva.1998.1816
发表时间: 1999-06
影响因子: 1.6
作者:
K. Fang;Runze Li
通讯作者: K. Fang;Runze Li
DOI: 10.1007/978-3-642-04107-5-3
发表时间: 2009-11
期刊: --
影响因子: --
作者:
C. Andrieu;Arnaud Doucet;R. Holenstein
通讯作者: C. Andrieu;Arnaud Doucet;R. Holenstein
DOI: 10.2307/2347392
发表时间: 1990-11
期刊: Applied statistics
影响因子: --
作者:
P. Cheek;P. McCullagh;J. Nelder
通讯作者: P. Cheek;P. McCullagh;J. Nelder
DOI: 10.1198/004017002320256422
发表时间: 2002-08
期刊: Technometrics
影响因子: 2.5
作者:
E. Ziegel
通讯作者: E. Ziegel