Title: Grey relational effort analysis technique using robust regression methods for individual projects

Authors: Geeta Nagpal; Moin Uddin; Arvinder Kaur

Addresses: Department of Computer Science and Engineering, National Institute of Technology, GT Road, Bye Pass, Jalandhar – 144011, Punjab, India ' Delhi Technological University, Shahbad Daulatpur, Main Bhawana Road, Delhi – 110042, India ' University School of Information Technology, Guru Gobind Singh Indraprastha University, Sector 16 C, Dwarka – 110075, Delhi, India

Abstract: Efficient development of software requires accurate estimates. It is unlikely to expect very accurate estimates of software development effort because of the inherent uncertainty in software development projects and the complex and dynamic interaction of factors that impact software development. In this study, two analogy methods based on integration of Grey Relational Effort Analysis Technique using Robust Regression Methods with and without feature subset selection have been proposed. In the previous, Grey Relational based effort estimation studies, GRA is used to assess similarity between projects with m features and effort is estimated from k most similar projects. In the proposed methodologies, the effort of the reference project is estimated by applying regression techniques to k most similar projects obtained using GRA as the similarity metric. Empirical results obtained are statistically significant, indicating that the methodology has great potential and can be used as a candidate approach for software effort estimation.

Keywords: software estimation; analogy; grey relational analysis; GRA; grey relational coefficient; grey relational grade; GRG; robust regression; feature subset selection; software development.

DOI: 10.1504/IJCISTUDIES.2014.058641

International Journal of Computational Intelligence Studies, 2014 Vol.3 No.1, pp.40 - 73

Received: 22 May 2012
Accepted: 05 Jul 2012
Published online: 28 Jun 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article