Confidence Intervals for Computational Effort Comparisons

Abstract. When researchers make alterations to the genetic programming algorithm they almost invariably wish to measure the change in performance of the evolutionary system. No one specific measure is standard, but Koza's computational effort statistic is frequently used [8]. In this paper the use of Koza's statistic is discussed and a study is made of three methods that produce confidence intervals for the statistic. It is found that an approximate 95% confidence interval can be easily produced.

• Type: Conference
• Year: 2007
• Where: EUROGP
• Authors: Matthew Walker, Howard Edwards, Chris H. Messom
• Keywords: Computational Effort Statistic, Confidence Interval, EUROGP 2007, Optimization, Researchers Make Alterations