In-process control of design inspection effectiveness

We present a methodology for the in-process control of design inspection focusing on escaped defects. The methodology estimates the defect escape probability at each phase in the process using the information available at the beginning of a particular phase. The development of the models is illustrated by a case involving data collected from the design inspections of software components. The data include the size of the product component, as well as the time invested in preparing for the inspection and actually carrying it out. After smoothing the original data with a clustering algorithm, to compensate for its excessive variability, a series of regression models exhibiting increasingly better fits to the data as more information becomes available was obtained. We discuss how management can use such models to reduce escape risk as the inspection process evolves.