Deriving and Verifying Statistical Distribution of a Hyperlink-Based Web Page Quality Metric

In this paper, we discuss issues related to metrics for Web page quality. These metrics are used for ranking the quality and relevance of Web pages in response to user needs. We focus on the problem of ascertaining the statistical distribution of some well-known hyperlink basedWebpage quality metrics. Based on empirical distributions ofWebpage degrees, we derived analytically the probability distribution for the Pagerank metric. We found out that it follows the familiar inverse polynomial lawrep orted for Webpage degrees. We verified the theoretical exercise with experimental results that suggest a highly concentrated distribution of the metric.