An important problem confronting decision makers is design of computer simulation experiments in settings where the assumptions usually made by statisticians are violated. The usual approach to this problem is to run until the money runs out and hope for the best. The present paper shows how to rationally design and analyze a computer simulation under minimal assumptions, using the Bishop-Dudewicz Heteroscedastic ANOVA (HANOVA) Procedures. This new HANOVA methodology is applied to multiple objective budgeting simulation. It is shown that significant differences, not detected in a previous study, exist between profits under different variance analysis methods. The HANOVA method is also applied to examine inflationary effects on U.S. corporation taxes.
展开▼