A Phase I Cluster-Based Method for Analyzing Nonparametric Profiles

dc.contributor.authorChen, Yajuanen
dc.contributor.authorBirch, Jeffrey B.en
dc.contributor.authorWoodall, William H.en
dc.contributor.departmentStatisticsen
dc.date.accessioned2019-05-08T19:46:20Zen
dc.date.available2019-05-08T19:46:20Zen
dc.date.issued2014en
dc.description.abstractA cluster-based method was used by Chen et al.²⁴ to analyze parametric profiles in Phase I of the profile monitoring process. They showed performance advantages in using their cluster-based method of analyzing parametric profiles over a non-cluster-based method with respect to more accurate estimates of the parameters and improved classification performance criteria. However, it is known that, in many cases, profiles can be better represented using a nonparametric method. In this study, we use the clusterbased method to analyze profiles that cannot be easily represented by a parametric function. The similarity matrix used during the clustering phase is based on the fits of the individual profiles with pspline regression. The clustering phase will determine an initial main cluster set which contains greater than half of the total profiles in the historical data set. The profiles with in-control T² statistics are sequentially added to the initial main cluster set and upon completion of the algorithm, the profiles in the main cluster set are classified as the in-control profiles and the profiles not in the main cluster set are classified as out-of-control profiles. A Monte Carlo study demonstrates that the cluster-based method results in superior performance over a non-cluster-based method with respect to better classification and higher power in detecting out-of-control profiles. Also, our Monte Carlo study shows that the clusterbased method has better performance than a non-cluster-based method whether the model is correctly specified or not. We illustrate the use of our method with data from the automotive industry.en
dc.format.extent27 pagesen
dc.format.mimetypeapplication/pdfen
dc.identifier.sourceurlhttps://www.stat.vt.edu/content/dam/stat_vt_edu/graphics-and-pdfs/research-papers/Technical_Reports/TechReport14-2.pdfen
dc.identifier.urihttp://hdl.handle.net/10919/89420en
dc.language.isoenen
dc.publisherVirginia Techen
dc.relation.ispartofseriesTechnical Report No. 14-2en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectMixed Modelsen
dc.subjectNonparametricen
dc.subjectProfile Monitoringen
dc.subjectRobusten
dc.subjectT² Statisticen
dc.titleA Phase I Cluster-Based Method for Analyzing Nonparametric Profilesen
dc.typeTechnical reporten
dc.type.dcmitypeTexten

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
TechReport14-2.pdf
Size:
954.15 KB
Format:
Adobe Portable Document Format