Taguchi, Genichi: Executive director of the American Supplier Institute, the director of the Japan Industrial Technology Institute and an honorary professor at Nanjing Institute of Technology in China. Taguchi is well-known for developing a methodology to improve quality and reduce costs, which, in the United States, is referred to as the Taguchi Methods. He also developed the quality loss function. He is an Honorary Member of ASQ.
Taguchi loss function: Parabolic approximation of the money lost to the customer due to a quality characteristic deviating from its target value. This function shows no loss at the target value, but loss increases exponentially as deviation increases from the target value, even within tolerance limits. Also called "nominal is better." This is a mathematical method to quantify the degree of achievement of the nominal the best value for the customer. The most important development from this concept is that parts deviating from nominal value have loss associated with them, even when they fall within tolerance limits. Conventional Western thinking is that anything within tolerance limits is good enough, as if it were the same no matter how close to nominal or how close to being out of tolerance. Use of the loss function encourages continual improvement instead of halting improvement when tolerances are barely met. This requires that the target value be the best value at the bottom of the parabola. The formula used to compute the quality loss function depends on the type of quality characteristic being used. (Quality Council of Indiana)
Taguchi Methods: The American Supplier Institute's trademarked term for the quality engineering methodology developed by Genichi Taguchi. In this engineering approach to quality control, Taguchi calls for off-line quality control, on-line quality control and a system of experimental design to improve quality and reduce costs.
Takt time: The rate of customer demand. Takt is the heartbeat of a lean system. Takt time is calculated by dividing production time by the quantity the customer requires in that time.
Tampering: Action taken to compensate for variation within the control limits of a stable system. Tampering increases rather than decreases variation, as evidenced in the funnel experiment.
Task: A specific, definable activity to perform an assigned piece of work, often finished within a certain time.
Team: A group of individuals organized to work together to accomplish a specific objective.
Test for normal probability: Used to check whether observations follow a normal distribution. P > 0.05 = data are normal.
Theory of constraints (TOC): Also called constraints management, it is a set of tools that examines the entire system for continuous improvement. The current reality tree, conflict resolution diagram, future reality tree, prerequisite tree and transition tree are the five tools used in its ongoing improvement process.
TL 9000: A quality management standard for the telecommunications industry built on ISO 9000. Its purpose is to define the requirements for the design, development, production, delivery, installation and maintenance of products and services. Included are cost and performance based measurements that measure reliability and quality performance of the products and services.
Tolerance: The maximum and minimum limit values a product may have and still meet customer requirements.
Tolerance design: A final stage is product design when allowable component tolerances are tightened if it is expected to avoid more quality loss than the economic loss due to the cost of tolerance tightening. (Quality Council of Indiana).
Tooling and Equipment (TE) Supplement: An interpretation of QS-9000 (see listing) developed by the Big Three automakers for tooling and equipment suppliers.
Top-management commitment: Participation of the highest level officials in their organization's quality improvement efforts. Their participation includes establishing and serving on a quality committee, establishing quality policies and goals, deploying those goals to lower levels of the organization, providing the resources and training lower levels need to achieve the goals, participating in quality improvement teams, reviewing progress organizationwide, recognizing those who have performed well and revising the current reward system to reflect the importance of achieving the quality goals.
Total productive maintenance (TPM): A series of methods, originally pioneered by Nippondenso (a member of the Toyota group), to ensure every machine in a production process is always able to perform its required tasks so that production is never interrupted.
Total quality: A strategic integrated system for achieving customer satisfaction that involves all managers and employees and uses quantitative methods to continuously improve an organization's processes.
Total quality control (TQC): A system that integrates quality development, maintenance and improvement of the parts of an organization. It helps a company economically manufacture its product and deliver its services.
Total quality management (TQM): A term initially coined by the Naval Air Systems Command to describe its Japanese style management approach to quality improvement. Since then, TQM has taken on many meanings. Simply put, it is a management approach to long-term success through customer satisfaction. TQM is based on the participation of all members of an organization in improving processes, products, services and the culture in which they work. The methods for implementing this approach are found in the teachings of such quality leaders as Philip B. Crosby, W. Edwards Deming, Armand V. Feigenbaum, Kaoru Ishikawa and Joseph M. Juran.
Transaction data: The finite data pertaining to a given event occurring in a process. Examples are the data obtained from an individual checking out groceries (the grocery shopping process) and the data obtained from testing a machined component (the final product inspection step of the production process).
Tree diagram: A management tool that depicts the hierarchy of tasks and subtasks needed to complete an objective. The finished diagram bears a resemblance to a tree.
Trend: The graphical representation of a variable's tendency, over time, to increase, decrease or remain unchanged.
Trend control chart: A control chart in which the deviation of the subgroup average, X-bar, from an expected trend in the process level is used to evaluate the stability of a process.
t-test: Assesses whether the means of two groups are statistically different from each other. Use this analysis if you want to compare the means of two groups.
Type I error: An incorrect decision to reject something (such as a statistical hypothesis or a lot of products) when it is acceptable.
Type II error: An incorrect decision to accept something when it is unacceptable.