Proceedings of the 30th conference on Winter simulation
Multiple predictor smoothing methods for sensitivity analysis
WSC '05 Proceedings of the 37th conference on Winter simulation
Sequential design and rational metamodelling
WSC '05 Proceedings of the 37th conference on Winter simulation
White noise assumptions revisited: regression metamodels and experimental designs in practice
Proceedings of the 38th conference on Winter simulation
A comprehensive review of methods for simulation output analysis
Proceedings of the 38th conference on Winter simulation
Simulation metamodels for modeling output distribution parameters
Proceedings of the 39th conference on Winter simulation: 40 years! The best is yet to come
Sequential designs for simulation experiments: nonlinear regression metamodeling
MIC '07 Proceedings of the 26th IASTED International Conference on Modelling, Identification, and Control
Allocation of simulation effort for neural network vs. regression metamodels
Proceedings of the Winter Simulation Conference
| Hi-index | 0.00 |
Metamodels are used for the analysis and optimization of real systems. The construction of a metamodel requires, in order to collect meaningful statistical data, a number of replicated simulation runs executed at each design point. We propose spreading those replications to an equal set of new neighboring design points. The resulting experimental design includes a single replication at each design point. The information collected from the additional points is balanced by a lack of statistical information from each point. Using smoothing techniques, we propose building the missing statistical information at each design point using the neighbors as approximate replications. This can lead to a better adjustment with less simulation runs. Two statistical tests are used to safeguard the applicability of the proposed procedure. Some examples are used to illustrate the increase in efficiency and approximation of the proposed approach.