Abstract
To assess measurement system variation, we propose an alternative to the standard plan that uses a random sample of parts to repeatedly measure. The new plan, called Leveraged Measurement System Assessment is conducted in two stages. In the first stage, called the baseline, a number of parts are measured once. In the second stage, we select a few extreme parts (based on their initial measurement in the baseline) and remeasure each of them a number of times. We demonstrate the advantage of the leveraged over the standard plan by comparing the bias and standard deviation of estimators of the intraclass correlation coefficient. We also present a method to determine sample size when planning a Leveraged Measurement System Assessment.