MUREM: A Multiplicative Regression Method for Software Development Effort Estimation

Autores/as

  • Ma. del Refugio Ofelia Luna Sandoval Centro Nacional de Investigación y Desarrollo Tecnológico
  • José Ruiz Ascencio Centro Nacional de Investigación y Desarrollo Tecnológico

DOI:

https://doi.org/10.13053/cys-20-4-2378

Palabras clave:

Software development effort estimation, method for estimating software development effort, estimating method, multiplicative method, regression model.

Resumen

Abstract. A multiplicative regression method to estimate software development effort is presented. This method, which we call MUREM, is a result of, on the one hand, a set of initial conditions to frame the process of estimating software development effort and, on the other hand, a set of restrictions to be satisfied by the development effort as a function of software size. To evaluate MUREM, a battery of hypothesis and standard statistical tests is applied to a large selection of well-known public databases, producing replicable experimental results. One important result shows the residuals pass criteria for white noise. MUREM improves state of the art estimates by correcting heteroscedasticity, increasing precision, yielding tighter confidence and prediction intervals and assuring the monotonicity and positivity of the function of size.

Biografía del autor/a

Ma. del Refugio Ofelia Luna Sandoval, Centro Nacional de Investigación y Desarrollo Tecnológico

Received a M.Sc. degree in Computer Science from the Centro Nacional de Investigación y Desarrollo Tecnológico (CENIDET), México, in 2011. She is currently a doctoral student at the CENIDET and her current research interests are applications of computational intelligence techniques to Software Engineering

José Ruiz Ascencio, Centro Nacional de Investigación y Desarrollo Tecnológico

Received the B. Sc. degree inphysics from (UNAM) in 1971, a M.Sc. degree fromStanford in 1973 and the D. Phil. degree from theUniversity of Sussex in 1989. He was researcherat the Institute of Applied Mathematics, IIMASUNAM,full-time lecturer at the AutonomousUniversity of Barcelona, automation project leaderfor Allen-Bradley, researcher at the InstitutoTecnológico de Monterrey, and invited scholar atMcGill University’s Center for Intelligent Machines(2003 and 2010). He joined CENIDET in 1995,where he is a member of the Artificial IntelligenceGroup. His current interests are machine visionand computational intelligence.

Descargas

Publicado

2016-12-18