Input data collection and analysis

This paper reviews perspectives and methods for specifying distribution and process forms and parameters from which observations are drawn to drive a stochastic simulation. All phases of input data analysis are covered, including data collection, choosing a modeling distribution, estimating parameters, and goodness-of-fit testing. A discussion is also presented concerning the debate over the desirability of fitting “standard” distributions to data as opposed to using a direct empirical distribution. Available software packages with a simulation orientation are also described.