...
首页> 外文期刊>Quality Control and Applied Statistics >Dynamic sampling allocation and design selection
【24h】

Dynamic sampling allocation and design selection

机译:动态采样分配和设计选择

获取原文
获取原文并翻译 | 示例
           

摘要

In this article, the problem of statistical selection in a general dynamic framework is considered. Particularly, the statistical selection problem of selecting the best from a finite set of alternatives is considered, where the best is determined regarding the largest mean, and the mean is inferred via statistical sampling. In this regard, the general framework of optimization problem for the optimal sampling allocation and design selection policy is defined. The structure of the optimal selection policy is presented with a simple motivational example followed by which an approximation algorithm is proposed. An approach for determining the factors of the optimal selection policy is then developed. For the allocation policy, an asymptotic policy called general Bayesian budget allocation is studied, which is comprised of a sampling statistic and a sequential rule. It is discussed that the optimal computing budget allocation algorithm can be interpreted as a special case of the asymptotical sampling statistics. Numerical examples are provided to illustrate the potential performance improvements with regard to small sample behavior and for comparison of various selection and allocation policies. (31 refs.)
机译:在本文中,考虑了一般动态框架中的统计选择问题。特别地,考虑了从有限的替代方案中选择最佳选择的统计选择问题,其中最佳地确定最大平均值,并且通过统计采样推断出平均值。在这方面,定义了最佳采样分配和设计选择策略的优化问题的一般框架。通过简单的动机示例呈现了最佳选择策略的结构,然后提出了近似算法。然后开发了一种确定最佳选择策略的因素的方法。对于分配政策,研究了称为普通贝叶斯预算分配的渐近政策,由采样统计和顺序规则组成。讨论了最佳计算预算分配算法可以被解释为渐近采样统计的特殊情况。提供了数值示例以说明关于小样本行为的潜在性能改进,以及用于各种选择和分配策略的比较。 (31参考文献)

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号