Abstract
This paper discusses the type of statistical techniques that will be required to formulate, evaluate and use the proposed REQUEST constructive quality model (COQUAMO). Statistical techniques are evaluated in terms of the probable nature and mode of use of COQUAMO, the requirements for model and metric validation, and the problems associated with software metrics data. Examples of preliminary evaluation of the proposed statistical techniques are given using genuine software metrics data.

This publication has 1 reference indexed in Scilit: