ABSTRACT
All test measurements are taken so that data that are useful in decision making may be acquired. No tests are run and no measurements made when the “answer” is already known. For data to be useful, it is necessary that their measurement errors be small in comparison to the changes or e¥ect under evaluation. Measurement error is unknown and unknowable. œis chapter addresses the techniques used to estimate, with some conŸdence, the expected limits of the measurement errors.
