Designing a Measurement Precision Experiment considering Distribution of Estimated Precision Measures

Evaluating performance of a measurement method is essential in metrology. Concepts of repeatability and reproducibility are introduced in ISO 5725 series including experiments (usually collaborative studies) to obtain these precision measures. ISO 5725 series mainly describes managerial part on how to run an experiment, but there is only a little guidance on statistical aspects of the experimental design. In such an experiment, accuracy of these precision measures is important, and the experimenter should be aware of biases and precisions of these precision measures. The objective of such an experiment is not limited to simply estimate the precision measures but to obtain these measures with intended accuracy. This paper proposed how to design a measurement precision experiment from statistical point of view. This paper first investigated the bias and precision of the precision measures based on their distributions and then proposed how to design an experiment with the desired accuracy.