Regression meetamodels and design of experiments

Simulation models are often used to support decision making for problems with uncertain inputs and parameters. Three types of models are used: deterministic, risk, and uncertainty models. Risk models are popular with researchers, but can be used only when the joint probability distribution of the in...

Full description

Saved in:
Bibliographic Details
Published inProceedings Winter Simulation Conference pp. 1433 - 1439
Main Authors van Groenendaal, W.J.H., Kleijnen, J.P.C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1996
Subjects
Analytical models
Decision making
Econometrics
Investments
Probability distribution
Risk analysis
Robustness
Stochastic processes
Uncertainty
US Department of Energy
Online AccessGet full text

Cover

More Information
Summary:Simulation models are often used to support decision making for problems with uncertain inputs and parameters. Three types of models are used: deterministic, risk, and uncertainty models. Risk models are popular with researchers, but can be used only when the joint probability distribution of the inputs and parameters is known. In many real-life situations, however, this is not the case. Uncertainty models are too restrictive for real-life situations. Therefore deterministic models are then used. The sensitivity of the results is often analyzed by changing one factor at a time or by simulating a few scenarios. This paper, however, shows that in case of uncertainty it might be better to apply design of experiments (DOE) in combination with regression metamodels.
ISBN:0780333837
9780780333833