Quality Assurance Terms Glossary/R
r Chart - A variables chart that monitors the dispersion of a process.
Randomness - A condition in which any individual event in a set of events has the same mathematical probability of occurrence as all other events. Random individual events are not predictable but a large number of them will form a definite pattern or distribution.
Random Sampling - Sample units that are selected in such a manner that all combinations of n units under consideration have an equal chance of being selected as the sample.
Random Variation - Variation that is uncontrollable.
Range - A measure of the variation in a set of data. It is calculated by subtracting the lowest value in the data set from the highest value in that same set.
Reactive Customer-Driven Quality - aka RCDC - A state that is characterized by a supplier “reacting” to the quality expectations of a customer rather than proactively anticipating customer needs and expectations.
Readiness - Used in a leadership context, the term refers to the extent to which a follower has the ability and willingness to accomplish a specific task.
Ready-Fire-Aim - A method that focuses on getting new technology to market and then determining how to sell the products.
Reality Tree - A cause-and-effect tree (current or future), construction of which is governed by rigorous rules of logic (one of the theory of constraints tools.
Recall Procedures - Steps for taking defective products from market. For example, tylenol and firestone wilderness at tires used these procedures to recall their products.
Red Bead Experiment - Carried out at each of Deming's 4-day seminars. Workers try to satisfy the customer by scooping out only white beads from a mixture of beads that is 80% white and 20% red . Each tries five times, all using the same tools and methods and under strict supervision (Deming!). Regardless of how hard people try to do well, results vary from one try to the next and "rankings" among the workers change. Lessons learned include: a) there is inherent (common cause) variation in every process; b) in such stable processes results we often view as individual "performance" are mostly due to the process or system, rather than the individual; c) there is not much the workers can do about the variation produced the problems must be corrected by management; d) ranking of individuals based on such performance measures in not only meaningless, but destructive to the individuals in the system. These are important and powerful lessons for anyone responsible for supervising or evaluating another person's performance.
Redundancy - A technique for avoiding failure by putting backup systems in place that can take over if a primary system fails. For example, many redundant systems are used on the space shuttle to protect the crew if a primary system fails.
Reengineering - (1) A method for making rapid, radical changes to a company’s organization and processes; (2) Taking apart a competitor’s products to see how they are designed and then designing similar products.
Regression aka Regression Analysis - A defined process for quantifying and modeling the output of a process relative o its input variables. It estimates the relationship between inputs and outputs of a process and produces mathematical model of that relationship. Its use can lead to a better understanding of the critical factors controlling ht equality of the process output.
Relationship Management - A method for developing long-term associations with customers.
Reliability - Propensity for failure of a product or component. The probability that an item will continue to function at customer expectation levels at a measurement point, under specified environmental and duty cycle conditions. The ability of an item to perform a required function under stated conditions.
Reliability Engineering - Engineering function dealing with the principles and practices related to the design, specification, assessment, and achievement of product or system reliability requirements and involving aspects of prediction, evaluation, production, and demonstration
Replications - Number of runs of an experiment.
Residual - The difference between a datum and the value predicted for it by a model. If linear regression is performed properly, the sum of the residuals from the regression line must be zero; otherwise, there is a computational error somewhere.
Residual Error - Experimental error
Response Surface Modeling - A process or product optimization technique, related to factorial experiments, that uses a “contour map” of the output variable as a function of two input variables. This map gives a way to discover and specify conditions of robust product and process performance.
Responsibility - A duty or obligation. In work, often those tasks, functions, processes or results which have been assigned to the individual which the individual is expected to do or to manage. In systems thinking, it is recognized that the "assignment of responsibility" does not mean that the "responsible" person or group of people actually has control over all the factors that affect the outcome. Too often, individuals or groups are blamed or credited undeservedly for the effects of the system (also see Accountability).
Responsiveness - A dimension of service quality that refers to the willingness of the service provider to be helpful and prompt in providing service.
Reprocess - taking a material (in-spec or out-of-spec) and reintroducing it to an existing (validated) process.
Reverse Engineering - The process of dismantling a competitor’s products to understand the strengths and weaknesses of the designs.
Reward System - In some cases this may refer only to such tangible elements as compensation and benefits, but typically this term also includes such intangible "rewards" as formal and informal recognition, praise or criticism, "perks", differential treatment by supervisors, being "included", access to information and many other considerations. Reward systems are powerful influences on organizational and employee behavior and need careful consideration and design to assure alignment with the aim and principles of the organization.
Rework - Activity or effort required to convert an otherwise unacceptable outcome of a process into an acceptable outcome.
Robust - A product or service designed in such a way that it can be readily produced in the presence of variation without defects or costly process treatment and with little variation or, to be designed to function properly in the presence of environmental variation.
Robust Design - Designing such that an increase in variability will not result in defective products.
Robust Process - A process with output variability that is not sensitive to the normal variation from its input variables.
Rolled Throughput Yield - aka - RTY
Root Cause - To prevent continuing recurrence of an undesirable outcome, problem-solvers need to "peel back the layers" to find the underlying or "root" causes. One technique for doing this is to ask "why did this happen?" And then to the reply to that question, ask "why?" Again. By the process of asking "why?" Several times in this fashion, one gets closer to the root cause. The early answers to the inquiries are more likely to be symptoms of more fundamental problems.
Root Cause Analysis - Study of original reason for nonconformance with a process. When the root cause is removed or corrected, the nonconformance will be eliminated.