Alternatives to regression models for estimating software projects

The use of ‘standard’ regression analysis to derive predictive equations for software development has recently been complemented by increasing numbers of analyses using less common methods, such as neural networks, fuzzy logic models, and regression trees. This paper considers the implications of using these methods and provides some recommendations as to when they may be appropriate. A comparison of techniques is also made in terms of their modelling capabilities with specific reference to function point analysis.

[1]  Gavin R. Finnie,et al.  Using Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort , 1994, Australas. J. Inf. Syst..

[2]  J. Verner,et al.  Software costing in practice , 1991 .

[3]  Adam A. Porter,et al.  Evaluating techniques for generating metric-based classification trees , 1990, J. Syst. Softw..

[4]  Y. Miyazaki,et al.  Robust regression for developing software estimation models , 1994, J. Syst. Softw..

[5]  Michael J. Prietula,et al.  Examining the Feasibility of a Case-Based Reasoning Model for Software Effort Estimation , 1992, MIS Q..

[6]  Stephen G. MacDonell.  Quantitative functional complexity analysis of commercial software systems , 1992 .

[7]  Douglas Fisher,et al.  Machine Learning Approaches to Estimating Software Development Effort , 1995, IEEE Trans. Software Eng..

[8]  Adam A. Porter,et al.  Learning from Examples: Generation and Evaluation of Decision Trees for Software Resource Analysis , 1988, IEEE Trans. Software Eng..

[9]  R Veryard,et al.  Information and software economics , 1989 .

[10]  Taghi M. Khoshgoftaar,et al.  A neural network approach for early detection of program modules having high risk in the maintenance phase , 1995, J. Syst. Softw..

[11]  Lesley M. Pickard,et al.  Statistical techniques for modelling software quality in the ESPIRIT REQUEST project , 1987 .

[12]  Barbara A. Kitchenham,et al.  Towards a constructive quality model. Part 2: Statistical techniques for modelling software quality in the ESPRIT REQUEST project , 1987, Softw. Eng. J..

[13]  Satish Kumar,et al.  Fuzzy systems and neural networks in software engineering project management , 1994, Applied Intelligence.

[14]  J. Hakkarainen,et al.  Neural networks in specification level software size estimation , 1993, [1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences.

[15]  Michael J. Watts,et al.  FuNN/2 - A Fuzzy Neural Network Architecture for Adaptive Learning and Knowledge Acquisition , 1997, Inf. Sci..

[16]  Maurice H. Halstead,et al.  Elements of software science , 1977 .

[17]  Robert A. Schowengerdt,et al.  A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification , 1995, IEEE Trans. Geosci. Remote. Sens..

[18]  Alan Myrvold.  Data analysis for software metrics , 1990, J. Syst. Softw..

[19]  Victor R. Basili,et al.  Tailoring the software process to project goals and environments , 1987, ICSE '87.

[20]  H. E. Dunsmore,et al.  Software engineering metrics and models , 1986 .

[21]  John W. Sheppard,et al.  Using a competitive learning neural network to evaluate software complexity , 1990, SIGSMALL '90.

[22]  Stephen G. MacDonell,et al.  A comparison of model building techniques to develop predictive equations for software metrics , 1997 .

[23]  L. Darrell Whitley,et al.  Prediction of Software Reliability Using Connectionist Models , 1992, IEEE Trans. Software Eng..