Threshold selection, hypothesis tests, and DOE methods
T. Beielstein, Sandor Markon · 2003
Threshold selection-a selection mechanism for noisy evolutionary algorithms-is put into the broader context of hypothesis testing. Optimal selection thresholds were derived theoretically. These theoretical results were used to find threshold values for a simple model of stochastic search and for a simplified elevator simulator. Design of experiments methods are used to validate the significance of the results.