Logo eprints

Metamodel variability in robust simulation-optimization: a bootstrap analysis

Dellino, Gabriella and Meloni, Carlo Metamodel variability in robust simulation-optimization: a bootstrap analysis. Technical Report (Unpublished)

WarningThere is a more recent version of this item available.
Full text not available from this repository.


Metamodels are often used in simulation-optimization for the design and management of complex systems. These metamodels yield insight into the relationship between responses and decision variables, providing fast analysis tools instead of the more expensive computer simulations. Moreover, these metamodels enable the integration of discipline-dependent analysis into the overall decision process. The use of stochastic simulation experiments and metamodels introduces a source of uncertainty in the decision process that we refer to as metamodel variability. To quantify this variability, we use bootstrapping. More speci�cally, we combine cross-validation and bootstrapping to simulate the metamodel construction process in stochastic environments. The resulting methodology is illustrated through the well-known Economic Order Quantity (EOQ) model using Kriging and regression metamodels. The relative validation errors are small, so they suggest that the metamodels give an adequate approximation, and bootstrapping these errors allows us to quantify the metamodels' variability in an acceptable way.

Item Type: Working Paper (Technical Report)
Uncontrolled Keywords: Simulation-optimization; metamodels; validation; bootstrap
Subjects: H Social Sciences > HB Economic Theory
Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Research Area: Economics and Institutional Change
Depositing User: Users 17 not found.
Date Deposited: 02 Aug 2011 09:36
Last Modified: 04 Aug 2011 07:30
URI: http://eprints.imtlucca.it/id/eprint/761

Available Versions of this Item

Actions (login required)

Edit Item Edit Item