A comparison study of two tests for detecting initialization bias in simulation output
Article Abstract:
This paper presents a comparison study of two statistical tests for detecting initialization bias in discrete-event simulation output. These two tests are the so-called optimal test and rank test developed and presented by Schruben et al. /1~ in 1983 and Vassilacopoulos /2~ in 1989 respectively. In the comparison experiments, artificially generated stochastic sequences are used as input to the tests. Such a sequence is obtained by embedding specified initialization bias into an unbiased stationary stochastic sequence. The results of the experiments have shown that both tests do perform satisfactorily in a similar way. It is noted that the optimal test is more sensitive to initialization bias, and therefore has consistently outperformed the rank tests when significant initialization bias is presented in the tested sequences. However, since the rank test is simpler to implement and easier to use than its counterpart, it is expected that it will also find wider acceptance and application in the future. (Reprinted by permission of the publisher.)
Publication Name: SIMULATION
Subject: Engineering and manufacturing industries
ISSN: 0037-5497
Year: 1993
User Contributions:
Comment about this article or add new information about this topic:
Bootstrap confidence intervals for estimating audit value from skewed populations and small samples
Article Abstract:
Classical estimation procedures that are often used in estimating the population audit value rely on the assumption of normality. Empirical evidence suggests however, that this may not be a valid assumption. Consequently, the use of normal theory methods may lead to erroneous or misleading conclusions. The bootstrap method is an effective alternative in many cases where the classical assumptions are in question. The bootstrap method replaces complex analytical techniques by computer intensive, simulation based, empirical analysis. This study illustrates the use of the bootstrap method in estimating the audit value from skewed populations and small samples. The results of Monte-Carlo simulations indicate that the bootstrap is more effective and efficient than the normal theory method. (Reprinted by permission of the publisher.)
Publication Name: SIMULATION
Subject: Engineering and manufacturing industries
ISSN: 0037-5497
Year: 1991
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: A simulation study of hardwood rootstock populations in young loblolly pine plantations. Simulation and object-oriented programming: the development of SERB
- Abstracts: A simulation model for management of operations in the pharmacy of a hospital. A methodology for simulation of database systems
- Abstracts: CSSL's and simulation of gas well behavior. HARVEST: a generalized animal population growth simulation
- Abstracts: A digital prescription for X-ray overload. Power electronics' polluting effects
- Abstracts: Macro requirement within a simulation interface. Simulation of main memory database recovery