Approval Criteria for Multivariate Measurement Systems
- Autores: Karl D. Majeske
- Localización: Journal of quality technology: A quarterly journal of methods applications and related topics, ISSN 0022-4065, Vol. 40, Nº. 2, 2008, págs. 140-153
- Idioma: inglés
- Enlaces
-
Resumen
Standard measurement-system analysis criteria assume a measuring device measures a single product characteristic to determine functionality. In automotive-body manufacturing, however, data are taken for many quality characteristics and each response is evaluated independently. This study develops multivariate extensions of gauge-approval criteria precision to tolerance ratio, percent repeatability and reproducibility (R&R), and signal to noise ratio. These criteria use the volume of constant-density contours to characterize variability. A MANOVA method is used to estimate the variance-covariance matrices for one-factor, two-factor, and three-factor gauge studies. It is shown how to fit the MANOVA model and estimate the multivariate criteria using automotive body panel gauge-study data.
