QUANTITATIVE-EVALUATION OF SOFTWARE PROCESS IMPROVEMENT

This article describes statistical analysis techniques and results used to quantitatively evaluate software process improvement. The analysis techniques include linear regression, rank correlation, and chi(2) tests that have been successfully used to quantitatively assess the software process of a large military subcontractor. A logical extension of this work is to examine the results of these statistical techniques after process improvement. We perform these investigations by altering original data to reflect varying types and degrees of process improvements and then repeating the statistical analyses. We find that different types of process improvement generate very different statistical results. The techniques and results presented here can be used to evaluate the effectiveness of process improvements and determine where continued process improvement is needed.