ABSTRACT
This chapter presents the use of simulation for decision modeling. The basic idea is to provide a model that will allow a mapping from the decision space to the outcome space. The chapter also presents the use of optimization methods as interfaced with simulations to allow for the analysis of decision situations with many, or even an infinite, number of alternatives. The key to a Monte Carlo simulation is the generation of random variates. A random variate value is an independent sample from a prescribed probability distribution, such as a normal distribution or a binomial distribution. The basic idea in the use of a simulation model for ranking alternatives is to execute the model with differing inputs and then rank the alternatives based on analyses of the outputs from the simulation. With respect to mean values, which are computed from the outputs of several independent replications of a simulation model, each individual output itself can represent a sample mean.
