A DEA–Tobit Analysis to Understand the Role of Experience and Task Factors in the Efficiency of Software Engineers

This study employs the data-envelopment analysis (DEA)-Tobit regression approach to analyze data from a leading software engineering organization to gain insights regarding the role of various types of technical experience and task factors in the efficiency of personnel assigned to software tasks. “Efficiency” follows a holistic-view definition as the quality and productivity achieved from the overall personnel experience, and it is evaluated with DEA. Then, a Tobit regression model is employed to determine the effect that various types of technical experience and task factors have on the DEA efficiency scores. Although the DEA-Tobit technique has been applied to various areas within the management science and operations research fields, it has not yet been presented as a general evaluation tool within the software-engineering field to understand drivers of software quality and productivity. We demonstrate how DEA-Tobit fills a gap not addressed by commonly applied methods in the literature.