Linda Weiser Friedman

Survey of Current Research

In a way, simulation metamodels have been with us for a long time. An explicit metamodel was never necessary in order to analyze simulation output data with such statistical techniques as t-est, paired t-est, one-way analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), factorial designs, blocking designs, factor analysis, discriminant analysis, even though these designs all assume an underlying general linear model.

Validating the simulation metamodel: Some practical approaches

This paper stresses the usefulness of developing a metamodel as an auxilliary model in simulation analysis and emphasizes the importance of validating the metamodel in order to determine whether it accurately approximates the simulation-generated data. A simulation model of the M/M/s queuing system was used for demonstration purposes. Two statistical validation procedures appropriate for simulation metamodels were discussed and demonstrated: use of a holdout sample and double cross- validation. The metamodel developed from the M/M/s queuing system simulation data proved to be valid as an approximation not only to the simulation but also to the real-world system itself.

Using Humor in the Introductory Statistics Course

This paper discusses reasons for using humor in the statistics classroom. Humor strengthens the relationship between student and teacher, reduces stress, makes a course more interesting, and, if relevant to the subject, may even enhance recall of the material. The authors provide examples of humorous material for teaching students such topics as descriptive statistics, probability and independence, sampling, confidence intervals, hypothesis testing, and regression and forecasting. Also, some references, summarized strategies, and suggestions for becoming more humorous in the classroom are provided.

The multivariate metamodel in queuing system simulation

Abstract This paper investigates the concept of a multiple-response metamodel in the simulation of queuing systems, as a means of establishing simplified, functional relationships with which inferences may be made to the real-world system of interest. Simulation metamodels were developed for two queuing systems: the M/M/s queue and a time-shared CPU queue. Results show that the multivariate simulation metamodel performed well in predicting values for the true performance characteristics and served as an aid to understanding the complex relationships underlying the real-world systems.

Analyzing Simulation Output Using the Bootstrap Method

There are many situations in which parametric statistical techniques are less than ideal for evaluating a simulated system. For most simulation output, one must rely heavily on the central limit theorein in order to apply parametric statistical techniques. The bootstrap statistic is a nonparametric sample-resample technique that makes no distributional assumptions and may be used for estimation and hypothesis testing. The authors propose the bootstrap as a valuable tool for the analysis of simulation output data since it can be used in situations in which either the distribution is not known or normal approximations are inappropriate. Furthermore, since bootstrapping is itself a simulation technique it is inherently satisfying as a tool for the analysis of simulation output data. Illustrations are presented.

Reducing the "wait" in waiting-line systems: Waiting line segmentation

The problem of long wait in queue in apparent wherever there is a waiting-line system, but the cost of waiting is not the same for all customers. The authors propose a new model of waiting, called Waiting Line Segmentation. Waiting lines are segmented into customers who are willing to pay a premium for faster service and those who are not. Analytic results show that this approach results in increased customer satisfaction for both segments, increased profits, and increased efficiency.

Tutorial: Statistical considerations in computer simulation: the state of the art†

The multiple response problem in simulation analysis refers to the statistical design and analysis of simulation experiments which output more than a single response variable, or measure of effectiveness. In this article, the multivariate response simulation model is defined and some historical solutions from the literature are discussed. Recent research into the use of multivariate statistical methods in simulation analysis is reviewed, including the statistical rationale for the use of these techniques, the advantage of using these methods in simulation output analysis, and a comprehensive survey of the simulation literature which has applied these procedures to date. The concept of multivariate response simulation metamodel, an auxiliary, analytic model which serves to aid in the interpretation of the simulation model, is also presented.

A framework for organizational success

The contention of this paper is that the marketing concept is but one aspect of a philosophy of business referred to by the authors as the framework for organizational success. This framework maintains that the marketing concept must work together with good management approaches and with ethical business practices in order to satisfy the needs and wants of the various publics of the organization — customers, employees, suppliers, society — and, in the long run, ensure the satisfaction of the needs of the organization itself. The authors propose that focusing on one concept, and ignoring the other two aspects, is not likely to promote organizational success.

The probability distribution as a performance criterion when comparing alternative systems

The Kolmogorov-Smirnov test is used to determine whether the output distributions of two simulated systems are significantly different. The advantages of using this statistical procedure, and the danger in making comparisons between the systems with only the mean as a critical performance measure, are dem onstrated. Two queuing systems were simulated and results analyzed first by comparing means and, then, distributions. Results showed that, even if the means of two alternative systems are equivalent, the systems may still prove to be significantly different from each other if the entire distribution is examined.

A New Kind of Marketing: Creating Micro-Niches Using Resonance Marketing

ABSTRACT Marketing has been dramatically changed by the Internet, the old rules do not apply. The Web allows companies to create products using micro-segmentation for target markets that are extremely small. Firms that want to be successful have to learn about resonance marketing. Resonance marketing used in conjunction with cause marketing and/or multicultural marketing can help a company find new market niches, charge premium prices. It can also be of great value to those interested in starting a small business.