A study on predictive performance of regression-based effort estimation models using base functional components

Authors:
Sousuke Amasaki;Tomoyuki Yokogawa
Affiliations:
Department of Systems Engineering, Okayama Prefectural University, Soja, Okayama, Japan;Department of Systems Engineering, Okayama Prefectural University, Soja, Okayama, Japan
Venue:
PROFES'12 Proceedings of the 13th international conference on Product-Focused Software Process Improvement
Year:
2012

Citing 5
Cited 0

Method to estimate parameter values in software prediction models

Information and Software Technology - Information and software economics
Software Estimation: Demystifying the Black Art

Software Estimation: Demystifying the Black Art
A Systematic Review of Software Development Cost Estimation Studies

IEEE Transactions on Software Engineering
Replicating studies on cross- vs single-company effort models using the ISBSG Database

Empirical Software Engineering
Comparative studies of the model evaluation criterions mmre and pred in software cost estimation research

Proceedings of the Second ACM-IEEE international symposium on Empirical software engineering and measurement

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some study claim that Base Functional Components (BFCs) contributes to effort at different levels and thus using BFCs instead of Function Points (FP) is better for effort estimation. This study examined the claim with sound filtration and extra-sample error, which were lacked in the past study. As a result, we confirmed that BFCs-based modelings used in the past study was statistically inferior to a FP-based model. We also demonstrated that a BFCs-based model could become comparable to the FP-based model with suitable transformations for BFCs. The result contributes to understand the importance of transformations for BFCs.