Abstract
In this paper, we provide a conceptual discussion of some of the limitations that we have found with Taguchi's approaches to product and process optimization, and provide some relatively simple-to-use alternatives that can help us to go beyond. Our main focus is on the difference between what we call ‘the one-shot approach’ and the sequential attitude to experimentation, an issue that makes a significant difference in practice. The objectives of this paper are to clarify some of the reasons for the controversy often surrounding Taguchi's statistical approaches, and to provide advice to engineers and managers about how to excel beyond Taguchi's original ideas. We conclude by pointing out how we can merge the best of Taguchi's excellent engineering ideas with other statistical approaches to come up with a highly competitive synthesis.