Service composition in service oriented architecture is an important activity. In regard to achieve the quality of service and secured activities from the web service compositions, they need to be verified about their impact towards fault proneness before deploying that service composition. Henceforth, here in this paper, we devised a novel statistical approach to assess the service composition impact scale towards fault proneness. The devised model explores the higher and lower ranges of the service composition impact scale, which is from the knowledge of earlier compositions that are notified as fault prone.