Optimization of Statistical Parameters Using Simulation

Keywords: Simulation, Statistical Optimization

Abstract: In this paper we develop strategies of a new iterative search procedure for finding the optimal statistical parameter of a noisy function that can be estimated through Monte Carlo simulation only.

In each iteration, two neighboring configurations are compared and the one that appears to be the better is passed on to the next iteration.The first strategy uses a single observation of each configuration in every iteration, while the second strtegy uses a fixed number of observatios of each configuration in every iteration. We will present some numerical results thet verfy the validity of our proposed search strategies.