Process investment and loss functions: Models and analysis

Numerous authors explore the relationship between investment in a production process to reduce its variance and improve quality levels. Recent studies also looked at reduction of process variance from a non-traditional Taguchi quality cost perspective. In this paper we propose and compare an alternative to Taguchi variance reduction models. We study the application of a modified form of the Reflected Normal loss function for optimal process investment/variance reduction decisions. We develop analytical models and investigate structural properties of the models. We derive optimal investment levels for reduction in process variance and provide several insights. We also establish guidelines for practitioners to choose amongst the two loss functions when considering investing in process improvement.