dc.creatorBraga, JWB
dc.creatorPoppi, RJ
dc.date2006
dc.date43831
dc.date2014-11-16T09:54:13Z
dc.date2015-11-26T16:21:32Z
dc.date2014-11-16T09:54:13Z
dc.date2015-11-26T16:21:32Z
dc.date.accessioned2018-03-28T23:03:31Z
dc.date.available2018-03-28T23:03:31Z
dc.identifierChemometrics And Intelligent Laboratory Systems. Elsevier Science Bv, v. 80, n. 1, n. 50, n. 56, 2006.
dc.identifier0169-7439
dc.identifierWOS:000234969400005
dc.identifier10.1016/j.chemolab.2005.06.004
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/56313
dc.identifierhttp://www.repositorio.unicamp.br/handle/REPOSIP/56313
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/56313
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1267968
dc.descriptionThis paper presents a study of the variance sources and confidence limits in two PLSR models for the determination of the polymorphic purity of Carbamazepine, using near and mid infrared spectroscopy. The variance sources estimated and compared were reference values, instrumental responses and fit of the model. The variance of instrumental responses was estimated experimentally and theoretically, and the differences were discussed. The confidence limits at three confidence levels: 95%, 90% and 50% were determined, presenting a good agreement with the expected values. The predictive ability of the models was compared, showing that both present the same overall performances with RMSEP of 0.67% for near infrared and 0.62% for mid infrared spectroscopy. It was also verified that, for both models, the main variance source remains the error of the PLSR model. (c) 2005 Elsevier B.V. All rights reserved.
dc.description80
dc.description1
dc.description50
dc.description56
dc.languageen
dc.publisherElsevier Science Bv
dc.publisherAmsterdam
dc.publisherHolanda
dc.relationChemometrics And Intelligent Laboratory Systems
dc.relationChemometrics Intell. Lab. Syst.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectprediction error
dc.subjectconfidence limits
dc.subjectuncertainty sources
dc.subjectpartial least squares regression
dc.subjectLeast-squares Regression
dc.subjectPrediction Error
dc.subjectStandard Error
dc.subjectMultivariate Calibration
dc.subjectReference Values
dc.subjectSpectroscopy
dc.subjectUnscrambler
dc.subjectUncertainty
dc.subjectCritique
dc.subjectExample
dc.titleComparison of variance sources and confidence limits in two PLSR models for determination of the polymorphic purity of carbamazepine
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución