ESTIMATION BY ANALOGY IN THE PERSPECTIVE EDUCATIONAL WEB HYPERMEDIA APPLICATIONS

The World Wide Web has become purely a hypermedia system these days. Numerous organizations have developed number of commercial and educational Web applications. The development of good quality applications has a high cost, mostly in time and amount of difficulty involved for the developers. On applying measurement techniques to measure the quality of applications and their development process, feedback can be obtained to help control, improve and predict products and process. Over the years numerous techniques for estimating development effort have been suggested by the various experts in the field of Web engineering. These techniques have been classified mainly as Expert judgment, algorithmic model, and Estimation by Analogy (machine learning). Now the Machine learning techniques are being used as a complement or an alternative to the previous two categories. Several studies have compared the prediction accuracy of these techniques, with emphasis placed on linear regression, stepwise regression, and Estimation by Analogy. The objective of this paper is to present a comparative study of the Estimation by Analogy techniques using result from one, two and three analogies and closest analogy among three to find the minimum Magnitude of Relative Error and to reach a conclusion for the best result that can be used for early cost estimation for any Web Hypermedia Application. The Web is a system of interlinked, hypertext documents that runs over the Internet. With the help of Web browser, a user can view Web page that may contain text, images and other multimedia and navigates between them using hyperlinks. The Web is simply defined as the universe of global network-accessible information [5]. Hypermedia applications are often advocated as the most powerful tool for a