Modified sequential bifurcation for simulation factor screening under skew-normal response model
Modified sequential bifurcation for simulation factor screening under skew-normal response model
复制标题
偏态正态响应模型下模拟因子筛选的改进序贯分岔
DOI：
10.1016/j.cie.2022.108274
复制
发表时间：
2022-05
影响因子：
7.9
通讯作者：
Yizhong Ma
中科院分区：
文献类型：
--
作者：
Lijun Liu;Jai-Hyun Byun;Chanseok Park;Yizhong Ma
·建立了描述非对称输出的偏正态响应模型。·提出了一种参数自举检验方法来检验因子的影响。·改进了偏态响应模型下的序贯分岔筛选方法。·验证了该方法的有效性和鲁棒性。序列分叉（SB）已广泛用于模拟因子筛选问题以识别重要因子（即，可以显著影响系统响应的因素），在“稀疏效应”假设下具有高效率和有效性。然而，当响应是不对称的，以前的SB研究的基础上的假设正态分布的响应显示在实践中的局限性。在本文中，我们开发了一个偏正态分布的响应模型，并提出了一个参数bootstrap检验程序，被纳入到每个“分叉”阶段的SB测试因素的显着性。数值实验证明了该方法的有效性。
• Skew-normal response model is developed to describe asymmetric outputs. • A parametric bootstrapping testing procedure is proposed for testing factors’ effects. • Sequential bifurcation is improved for screening under skew-normal response model. • The proposed method is validated on effectiveness and robustness. Sequential bifurcation (SB) has been widely used for simulation factor screening problems to identify important factors (i.e., factors that can significantly affect system response) with high efficiency and effectiveness under the ‘sparse effects’ assumption. However, when the response is asymmetric, previous SB studies based on the assumption of normally distributed response have shown limitations in practice. In this paper, we develop a skew-normal distributed response model and propose a parametric bootstrap testing procedure that is incorporated into every ‘bifurcation’ stage of SB for testing the significance of factors. Numerical experiments are provided to demonstrate the effectiveness and efficiency of the screening methods.
登录
查看更多内容
影响因子：
8.1
作者：
Ge, Qiao;Menendez, Monica
通讯作者：
Menendez, Monica
影响因子：
2.3
作者：
Jyun-You Chiang;Tzong-Ru Tsai;Nan-Cheng Su
通讯作者：
Jyun-You Chiang;Tzong-Ru Tsai;Nan-Cheng Su
DOI：
10.1016/j.ejor.2008.09.005
发表时间：
2005-12
期刊：
Proceedings of the Winter Simulation Conference, 2005.
影响因子：
--
作者：
Hua Shen;H. Wan
通讯作者：
Hua Shen;H. Wan
影响因子：
--
作者：
P. Goethals;B. Cho
通讯作者：
P. Goethals;B. Cho
DOI：
10.1145/2651364
发表时间：
2014-12
期刊：
ACM Transactions on Modeling and Computer Simulation (TOMACS)
影响因子：
--
作者：
Bruce E. Ankenman;R. Cheng;S. Lewis
通讯作者：
Bruce E. Ankenman;R. Cheng;S. Lewis