Showing papers by "Barry L. Nelson published in 1992"

Evaluation of tests for initial-condition bias

Abstract: We evaluate, theoretically and empirically, the power of a family of tests for initial-condition bias.

Designing efficient simulation experiments

Abstract: This tutorial describes basic principles for designing st artistically efficient simulation experiments and controlling experiment error, including the use of explorat or y experiments, assignment of random number seeds or streams, and analysis of the results. Simulation experiments that are performed to compare two or more systems are emphasized.

Multivariate batch means and control variates

Abstract: We consider applying the nonoverlapping batch means output analysis method in conjunction with the control-variate variance-reduction technique to estimate a steady-state multivariate mean vector. The effects of the number of batches and the number of control variates on the multivariate point and region estimators and the univariate point and interval estimators are considered. The results are experiment analysis guidelines in terms of an appropriate range of the number of batches to choose as a function of the number of responses and control variates. The results have implications for terminating simulations as well.

Representation of user transaction processing behavior with a state transition matrix

Abstract: A new method of modeling user sessions as Markov chains using NxN transition matrices is presented. These matrices are used to provide the user transaction sequences for discrete event simulation models of an online transaction processing system. Methods are given for validating the matrices, and algorithms are provided for modifying the matrices. Methodology for implementation in SLAM II@ is given. This method allows the realistic simulation of user behavior and can also be used as the control for load generators for system level tests. Using comparisons of two matrices, one may compare the behavior of two different user populations.

Heteroscedastic multiple comparison procedures for computer simulation

Abstract: We consider comparing a small, finite number of stochastic systems via computer simulation We use a transformation called batching to change our stochastic systems' data to approximately independent and normally distributed data Our goal is to find the system with the largest expected performance We achieve this goal by using a class of confidence interval procedures known as Multiple Comparisons with the Best (MCB) MCB is a method that provides joint confidence intervals for the difference between the performance of each individual system and the (unknown) best system Other MCB procedures precede this work, but our procedures uniquely allow for the unknown variances of the data to be different across systems Unfortunately, an exact solution to our problem for single samples from each system would imply an exact solution to the Behrens-Fisher problem Fortunately, there are a few approximate solutions to the Behrens-Fisher problem, and we extend one of them (the Welch moment approximation) to address our problem In addition, we describe exact (generalized-means) and conservative (means) procedures that require two sampling stages from each system, as is common in simulation studies The one-stage procedures we derive allow simulators to study their experiments results after the experiments are concluded, but do not provide convenient experimental designs Two stage procedures have advantages over the one-stage procedures: They work with pilot results, require mild variance assumptions, and guarantee inference at a fixed precision Both our one-stage and two-stage procedures could be easily incorporated into simulation packages Although our research focuses on computer simulation experiments, our results apply to other settings including laboratory, work-place, and historical studies Further, this work contributes to Statistics literature by describing heteroscedastic MCB Additionally, MCB is introduced in an alternative manner using Hsu's Lemmas