Abstract
A computational experiment uses a computer model to make inferences about some underlying system. This type of experiment can be seen as a branch of applied statistics, because the user must take into account three sources of uncertainty. First, the models often contain parameters whose values are not certain; second, the models themselves are imperfect representations of the underlying system; and third, data collected from the system that might be used to calibrate the models are imperfectly measured. Study of multiple experiments involves two aspects: experimental planning, and analysis and modeling of experimental results. In this chapter, we will do 6 computer experiments containing 55 runs with our multi-agent based artificial society.