Abstract
This article presents a methodology for approving a measurement system when the variable of interest is not directly measured. Rather, the manufacturer measures some other related variables to derive or predict the quality characteristic. To approve the measurement system, one must estimate error in each measured value and then, using either variable transformation or a Taylor series approximation, propagate these errors through the calculation to obtain an error distribution for the derived values. An evaluation of a measurement system used to measure the friction of automotive brake pads—derived from force and torque measurements—demonstrates the methodology.