Taylor & Francis Group
Browse
1/1
2 files

Adaptive Minimum Confidence Region Rule for Multivariate Initialization Bias Truncation in Discrete-Event Simulations

Version 3 2019-10-18, 18:28
Version 2 2019-10-15, 12:19
Version 1 2019-09-16, 18:44
dataset
posted on 2019-10-18, 18:28 authored by Jianguo Wu, Honglun Xu, Feng Ju, Tzu-Liang (Bill) Tseng

Initialization bias truncation is critically important for system performance assessment and warm-up length estimation in discrete-event simulations. Most of the existing methods are for univariate signals, while multivariate truncation has been rarely studied. To fill such gap, this article proposes an efficient method, called adaptive minimum confidence region rule (AMCR) for multivariate initialization bias truncation. It determines the truncation point by minimizing the modified confidence volume with a tuning parameter for the mean estimate. An elbow method is developed for adaptive selection of the tuning parameter. Theoretical properties of the AMCR rule for both data with and without autocorrelations have been derived for justification and practical guidance. The effectiveness and superiority of the AMCR rule over other existing approaches have been demonstrated through thorough numerical studies and real application. Supplementary materials for this article are available online.

Funding

Jianguo Wu was partially supported by National Natural Science Foundation of China grant NSFC-51875003 and key program NSFC-71932006. Feng Ju was partially supported by the National Science Foundation grant NSF CMMI-1829238.

History