Simulation Modeling and Analysis
Simulation Modeling and Analysis
Accounting for input model and parameter uncertainty in simulation
Proceedings of the 33nd conference on Winter simulation
Accounting for input model and parameter uncertainty in simulation
Proceedings of the 33nd conference on Winter simulation
Input modeling: input model uncertainty: why do we care and what should we do about it?
Proceedings of the 35th conference on Winter simulation: driving innovation
Simulation input modeling: a kernel approach to estimating the density of a conditional expectation
Proceedings of the 35th conference on Winter simulation: driving innovation
Determining output uncertainty of computer system models
Performance Evaluation
Reliable simulation with input uncertainties using an interval-based approach
Proceedings of the 40th Conference on Winter Simulation
A simple model for assessing output uncertainty in stochastic simulation systems
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
On the Accuracy of Ad Hoc Distributed Simulations for Open Queueing Network
PADS '11 Proceedings of the 2011 IEEE Workshop on Principles of Advanced and Distributed Simulation
A framework for input uncertainty analysis
Proceedings of the Winter Simulation Conference
| Hi-index | 0.01 |
We formulate and evaluate a Bayesian approach to probabilistic input modeling. Taking into account the parameter and stochastic uncertainties inherent in most simulations, this approach yields valid predictive inferences about the output quantities of interest. We use prior information to construct prior distributions on the input-model parameters. Combining this prior information with the likelihood function of sample data observed on the input processes, we compute the posterior parameter distributions using Bayes' rule. This leads to a Bayesian Simulation Replication Algorithm in which: (a) we estimate the parameter uncertainty by sampling from the posterior distribution of the input model's parameters on selected simulation runs; and (b) we estimate the stochastic uncertainty by multiple independent replications of those selected runs. We also formulate some performance evaluation criteria that are reasonable within both the Bayesian and frequentist paradigms. An experimental performance evaluation demonstrates the advantages of the Bayesian approach versus conventional frequentist techniques.