An empirical analysis of software effort estimation with outlier elimination

  • Authors:
  • Yeong-Seok Seo;Kyung-A Yoon;Doo-Hwan Bae

  • Affiliations:
  • Software engineering laboratory, Division of Computer Science, EECS, KAIST, South Korea;Software engineering laboratory, Division of Computer Science, EECS, KAIST, South Korea;Software engineering laboratory, Division of Computer Science, EECS, KAIST, South Korea

  • Venue:
  • Proceedings of the 4th international workshop on Predictor models in software engineering
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Accurate software effort estimation has always been challenge for software engineering communities. To improve the estimation accuracy of software effort, many studies have focused on effort estimation methods without any consideration of data quality, although data quality is one of important factors to impact to the estimation accuracy. In this paper, we investigate the influence of outlier elimination upon the accuracy of software effort estimation through empirical studies applying two outlier elimination methods(Least trimmed square and K-means clustering) and three effort estimation methods( Least squares, Neural network and Bayesian network) associatively. The empirical studies are performed using two industry data sets(the ISBSG Release 9 and the Bank data set which consists of the project data performed in a bank in Korea) with or without outlier elimination.