Measurement systems include variation and error, just like any other process. When a characteristic is measured the readings that are recorded include this measurement error.
It is easy to overlook this and assume that measurements reflect the true value of the characteristic. This can result in fruitless attempts to improve the process when the apparent variation is caused by variations in the measuring system. Measurement Systems Analysis should be an essential precursor to introducing Statistical Process Control, or using Design of Experiments.
Topics that are associated with measurement systems analysis include: