Elizabeth Murff

The Relative Efficiency of Ranked Set Sampling in Ordinary Least Squares Regression

Ranked set sampling was developed for situations where measurement cost is expensive compared with unit acquisition. This paper presents results of simulations and theory examining the impact of balanced ranked set sampling on the relative efficiencies of the slope and intercept estimators of an ordinary least squares regression. Perfect ranking of either the independent or the dependent variable is assumed throughout. In contradistinction to most of the published ranked set sampling work, it is demonstrated that balanced ranked set sampling offers at most little improvement in the relative efficiencies of the slope estimator at any sample size.

Repurposing an Old Game for an International World

The game SO LONG SUCKER was designed in the United States in 1964 with the aim of showing how potentially unethical behavior necessary for winning was inherent in the game’s incentive structure. Sessions with East Asian participants, however, led to very different game dynamics in which collaborative rather than antagonistic behaviors occurred. This confirms that the course of a simulation game run is determined by more than its rules and roles. The participants’ personalities, skills, personal histories, and preexisting relationships also play a role. Furthermore, the unwritten rules of social behavior that the participants have been socialized into, their culture, is of crucial importance. This article uses experiences with a mix of U.S. and Taiwanese participants to discuss the interaction of written and unwritten rules in determining game dynamics. The suitability for international classroom use of this game, and others, as a vehicle for drawing lessons about culture is argued.

Beyond the gold and pray equation: introducing interrelationships in industry-level unit demand equations for business games

Product unit demand is determined by many factors in business simulations; among these are the marketing variables of price, place, promotion, and quality. In the actual marketplace, however, these variables are not independent as is assumed by many simulation algorithms in the literature. This article discusses the need for and development of a two-attribute multiple-market-segment industry-level unit demand equation that explicitly includes the correlation between the two variables that affect demand (price and promotion) that form the domain of the unit demand equation for the model described in this article.

Changing the World Through Meaningful Play

This article reports on the International Simulation and Gaming Association’s conference in Spokane, Washington, United States (ISAGA2010). It provides an overview of the many presentations and workshops at the conference, as well as hints of other events both planned and unplanned.

Some Common Problems with Statistics in Papers and Presentations

It is always a struggle to write papers and talks that contain statistical information as the presentation methods used for analytic results do have an impact on the comprehension of the reader or audience. Furthermore, fundamental statistics are often misunderstood or obscured by the author rather than clearly explained. The fact that one can never be sure of the statistical sophistication of a reader or audience makes it easy for the author to write material that muddles rather than clarifies the results. Then, the reader or audience is left wondering if the author’s work is just “lies, damn lies, or statistics”. This paper provides a short discourse on fundamental statistical theory, intermixed with a few thoughts and suggestions on the use and presentation of statistical results. After all, any paper or presentation is useless if the intended audience misunderstands or misinterprets the information being presented.