A Simulation Tool for Efficient Analogy Based Cost Estimation

  • Authors:

  • L. Angelis;I. Stamelos

  • Affiliations:

  • Department of Informatics, Aristotle University of Thessaloniki, 54006, Thessaloniki, GREECE;Department of Informatics, Aristotle University of Thessaloniki, 54006, Thessaloniki, GREECE

  • Venue:
  • Empirical Software Engineering
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

Estimation of a softwareproject effort, based on project analogies, is a promising methodin the area of software cost estimation. Projects in a historicaldatabase, that are analogous (similar) to the project under examination,are detected, and their effort data are used to produce estimates.As in all software cost estimation approaches, important decisionsmust be made regarding certain parameters, in order to calibratewith local data and obtain reliable estimates. In this paper,we present a statistical simulation tool, namely the bootstrapmethod, which helps the user in tuning the analogy approach beforeapplication to real projects. This is an essential step of themethod, because if inappropriate values for the parameters areselected in the first place, the estimate will be inevitablywrong. Additionally, we show how measures of accuracy and inparticular, confidence intervals, may be computed for the analogy-basedestimates, using the bootstrap method with different assumptionsabout the population distribution of the data set. Estimate confidenceintervals are necessary in order to assess point estimate accuracyand assist risk analysis and project planning. Examples of bootstrapconfidence intervals and a comparison with regression modelsare presented on well-known cost data sets.