Confidence intervals for computational effort comparisons

Matthew Walker, Howard Edwards, Chris Messom

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

12 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationGenetic Programming - 10th European Conference, EuroGP 2007 Proceedings
Number of pages10
Volume4445 LNCS
Publication statusPublished - 2007
Externally publishedYes
Event10th European Conference on Genetic Programming, EuroGP 2007 - Valencia, Spain
Duration: 11 Apr 200713 Apr 2007


Conference10th European Conference on Genetic Programming, EuroGP 2007

Cite this