Reliability and statistics

Defect detection tests are among the more commonly employed of non-destructive tests. The evaluation of NDT reliability commonly contains two statistical errors. First, most tests fail to define the objects that are called “sampling units” in statistics; it follows that the reliability of the tests cannot be established. Second, the literature usually misuses statistical terms in such a way as to make it sound as though sampling units are defined. These two errors may lead to incorrect estimates of probability of detection.