An Empirical Study of Effort Estimation Using Simplified Functional Point Analysis

Abstract

An important task in software development is to estimate the effort needed for developing software, which is the major cost of a software project. The success of a project greatly depends on the accuracy of estimation. Although a variety of estimation models have been proposed, practitioners still experience difficulties in applying these methods to modern applications because most models attempt to cover all possible factors related to size, and therefore effort. As a result, these generic models are too complicated or difficult to be implemented, which becomes an obstacle for their acceptance by practitioners. We present a different approach in this paper: instead of developing a generic model that is more comprehensive and complete, we simplify and tailor a popular estimation model, Function Point Analysis (FPA), so that it is specific and incorporate more of an application’s characteristics. The empirical study shows that the accuracy of the simplified model is comparable with that of the full-fledged FPA.