Level: Advanced
【Presenter】
Keio University Graduate School of Health Management
Visiting Professor Takenori Takahashi
[Presentation overview]
A superdesign is an analytical design using a superstructure function, which is a double structure function based on superfactors. This method increases the possibility of design and enables advanced design that was not possible in the past. However, early superdesigns require that the entire interval can be approximated by a single function with high accuracy. However, in recent years, the number of experiments with a large number of levels has increased, and when the number of levels is around 10 or more, it becomes difficult to approximate the entire interval with a single function with high accuracy. In such cases, it is reasonable to use a composite approximation that divides the entire interval into subintervals and approximates each interval with high accuracy. However, as a result, the number of parameters (coefficients) to be dealt with in the design increases remarkably, so it is necessary to deal with it. This research introduces a method for that purpose. In addition, flexible and advanced design is difficult with the analysis of variance approach, but is possible with mathematical programming. What is important at this time is the approach of turning the "design PDCA cycle". In this study, design is regarded as consensus building among stakeholders, and we propose a method to realize it by the approach of ``design PDCA cycle'' based on mathematical programming. As an advanced application, we also discuss a flexible design in which superfactors can be freely specified.
[Profile of the presenter]
I have been researching TQM (Total Quality Management), SQM (Statistical Quality Management) and design theory for nearly 50 years. Since the beginning of the 21st century, we have proposed a new design paradigm, Hyper Design, and developed the HOPE theory (Hyper Optimization for Prospective Engineering), which is the mathematics of the new design paradigm. are jointly developing Through this effort, we have realized a new design method based on the trinity of "super-design" as a way of thinking, "HOPE theory" as statistical mathematics, and "HOPE-Add-in for JMP" as a support tool. As a social scientific extension of this theory, he advocated selective two-sided causal analysis ([multigroup principal component regression analysis] as front side causal analysis + [factor regression analysis] as back side causal analysis). We propose reverse causal analysis (causal analysis method corresponding to quasi-SEM), which is an advanced approach after causal analysis.
