Selection of the Best Using Simulation Models | ||||
The Egyptian Statistical Journal | ||||
Article 4, Volume 49, Issue 2, December 2005, Page 144-166 | ||||
Document Type: Original Article | ||||
DOI: 10.21608/esju.2005.313562 | ||||
View on SCiNiTO | ||||
Abstract | ||||
This paper discusses the validity of using common random numbers (CRNs) with two-stage selection procedures to improve the possibility of correct selection. We propose using CRNS with Rinott's two-stage selection (RN) and enhanced two-stage selection (ETSS) procedures when the underlying processes satisfy certain conditions. Moreover, this paper studies another modification of RN and ETSS procedures. The modification, which is appropriate for use in the simulation environment, uses in the procedures' first stage different variance estimators than the usual batch means (BM) variance estimator. In particular, we will use variance estimators arising from the method of standardized time series (STS). A Mont Carlo experimental performance evaluation demonstrates the trade-offs involving the possibility of correct selection and expected sample size of using CRNS and STS with two-stage selection procedures. | ||||
Keywords | ||||
Simulation; Two; Stage Selection Procedures; Rinott's Two; Enhanced Two; Stage Selection Procedure; Common Random Numbers; Standardized Time Series | ||||
Statistics Article View: 22 |
||||