Integrating data collection and model analysis in simulation

In this thesis we consider simulation project dynamics from a high level and examine some ways for relating the activities of data collection, model analysis, and decision making. The main goals are to quantify the uncertainty in decisions caused by input process estimation, and to decide how data should be collected and analyzed to minimize this uncertainty.; Several different techniques are explored. We use designed experiments to identify important unknown parameters and guide subsequent data collection. We also develop sequential response surface models that allow us to make simulation runs concurrently with data collection. The ideas are illustrated with a number of computational examples.