Keebom Kang

An investigation of finite-sample behavior of confidence interval estimators

We investigate the small-sample behavior and convergence properties of confidence interval estimators (CIEs) for the mean of a stationary discrete process. We consider CIEs arising from nonoverlapping batch means, overlapping batch means, and standardized time series, all of which are commonly used in discrete-event simulation. The performance measures of interest are the coverage probability, and the expected value and variance of the half-length. We use empirical and analytical methods to make detailed comparisons regarding the behavior of the CIEs for a variety of stochastic processes. All the CIEs under study are asymptotically valid; however, they are usually invalid for small sample sizes. We find that for small samples, the bias of the variance parameter estimator figures significantly in CIE coverage performance—the less bias the better. A secondary role is played by the marginal distribution of the stationary process. We also point out that some CIEs require fewer observations before manifesting ...

Staging queues in material handling and transportation systems

In most physical queueing applications, customers join a queue and move forward after each service, leaving room for others to join behind them. Some queues found in material handling and transportation systems do not operate like this because the queued entities (pallets or unoccupied cars, for example) are incapable of moving forward autonomously. We develop a model for the resulting staging queue, and give simulation results for several configurations.

Properties of batch means from stationary ARMA time series

The batch-means process arising from an arbitary autoregressive moving-average (ARMA) process time series is derived. As side results, the variance and correlation structures of the batch-means process as functions of the batch size and parameters of the original process are obtained. Except for the first-order ARMA process, for which a closed-form expression is obtained, the parameters of the batch-means process are determined numerically.

The Correlation Between Mean and Variance Estimators in Computer Simulation

Abstract Consider the problem of estimating confidence intervals for the mean of a stationary stochastic process. Denote the point estimator for the process mean by , and let be an estimator for limn −∞nVar(), the variance parameter. In this paper, we derive expressions for the correlation between and for various variance parameter estimators and stochastic processes. Among the variance estimators under study are those arising from the methods of nonoverlapping batched means, overlapping batched means, and standardized time series. Also, we empirically examine the relationships between Corr( ) and Confidence interval estimator performance; we see that Corr( ) affects the symmetry of confidence interval coverage, but not necessarily the actual coverage.

Simulation of transportation logistics

In this paper, we discuss issues concerning the simulation of transportation systems. In particular, we demonstrate a number of implementation tricks that are designed to make the modeling and coding processes more efficient and transparent. We present examples involving the simulation of commercial airline and military sealift operations.

Cycle time reduction for naval aviation depots

We describe two simulation models for repair processes of aircraft in the Navy, and suggest ways to reduce cycle time and improve readiness. The models illustrate the effects of material availability and process redesign on repair cycle time and work-in-process inventory levels for critical components. Our results indicate that the Navy could significantly reduce repair cycle times of those components by increasing stock levels of relatively inexpensive repair parts and slightly modifying current repair processes.

Statistical properties of out-of-frame detection schemes for digital transmission systems

The importance of the misframe times for DS1 frame synchronization has often been addressed in designing and using network elements and mediation units. By extending the work of J. H. Eu and W. W. Rollins (1991), Markov chain first passage time analysis is used to derive higher moments of the misframe times in both random and burst error environments. This methodology is of great value in evaluating frame synchronization techniques for digital transmission systems. By experimenting with several out-of-frame detection schemes and reasonable values for bit error ratio (BER), it is shown that misframe times are always approximately exponentially distributed for all schemes. >

Cramer-von Mises variance estimators for simulations

The authors study estimators for the variance parameter sigma /sup 2/ of a stationary process. The estimators are based on weighted Cramer-von Mises statistics formed from the standardized time series of the process. Certain weightings yield estimators which are first-order unbiased for sigma /sup 2/ and which have low variance. It is also shown how the Cramer-von Mises estimators are related to the standardized time series area estimator; this relationship is used to establish additional estimators for sigma /sup 2/.<<ETX>>

Graphical Methods for Evaluating and Comparing Confidence-Interval Procedures

We discuss various coverage-surface plots and scatter plots for evaluating and comparing confidence-interval procedures.

Sea based logistics: distribution problems for future global contingencies

Proceedings of the 1997 Winter Simulation Conference ed. S. Andradottir, K. J. Healy, D. H. Withers, and B. L. Nelson