Assessing a binary measurement system: A new plan using targeted verification with conditional sampling and baseline information. (November 2019)

• Record Type: Journal Article
• Authors: Severn, Daniel E.; Steiner, Stefan H.; MacKay, R. Jock
• Is Part Of: Measurement. Volume 146(2019)
• Page Start: 101
• Page End: 109
• Publication Date: 2019-11
• Subjects: Baseline data -- Binary measurement system assessment -- Conditional sampling -- Targeted verification; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2019.06.019
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Estimate misclassification rates for non-destructive pass/fail inspection system. Efficient plans using available data, repeated measurement & conditional sampling. Demonstrated improvement to existing assessment plans. Abstract: We investigate efficient plans to assess the misclassification error rates of a binary measurement system used as an in-line inspection protocol. We assume that parts can be inspected repeatedly and that each part has its own (latent) misclassification rate. We propose a three-phase assessment plan. Phase I consists of data from recent inspection history. In Phase II, we select a sample of failed parts that we re-measure multiple times with the binary measurement system of interest. In Phase III, we verify a carefully selected subsample of the parts from Phase II with the aid of a binary gold standard measurement system. We show that the proposed plan is a substantial improvement over existing assessment plans in terms of cost and/or precision.