Sensitivity Analysis of Simulation Experiments: Regression Analysis andStatistical Design. A Contribution to the European Simulation Meeting on Problem Solving by Simulation. Held in Esztergom, Hungary on August 23-30, 1990

摘要

The tutorial gives a survey of strategic issues in the statistical design andanalysis of experiments with deterministic and random simulation models. These issues concern what-if analysis, optimization, and so on. The analysis uses regression (meta)models and Least Squares. The design uses classical experimental designs such as 2 sup (k-p) factorials, which are efficient and effective. If there are very many inputs, then special techniques such as group screening and sequential bifurcation are useful. Applications are discussed.