Model validation and error estimation in multi-block partial least squares regression

作     者：Hassani, Sahar Martens, Harald Qannari, El Mostafa Hanafi, Mohamed Kohler, Achim 

作者机构：Nofima Mat AS Norwegian Food Res Inst N-1430 As Norway Norwegian Univ Life Sci Dept Math Sci & Technol IMT Ctr Integrat Genet CIGENE N-1432 As Norway ONIRIS INRA Unite Sensometrie & Chimiometrie F-44322 Nantes 3 France 

出 版 物：《CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS》 (化学计量学与智能实验系统)

年 卷 期：2012年第117卷

页      面：42-53页

核心收录：

学科分类：07[理学] 0804[工学-仪器科学与技术] 0714[理学-统计学（可授理学、经济学学位）] 0703[理学-化学] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Multi-block methods Multi-block Partial Least Squares Regression (MBPLSR) Validation tools Cross validation Number of components 

摘      要：While validation of Partial Least Squares Regression (PLSR) models has been discussed extensively, validation tools that are tailored to Multi-block Partial Least Squares Regression (MBPLSR) have not been discussed in literature yet. This paper introduces validation tools for estimating predictive ability and model stability in MBPLSR models on block level and on global level. Predictive ability on the block level and global level are estimated by calculating the predictive power of block and global parameters. Model stability is estimated by checking the stability of block model parameters and global parameters. By comparing error plots for model stability and predictive ability the user can decide on the number of component to be used. The number of components to be chosen depends on the data set and the purpose of the investigation. (C) 2011 Elsevier B.V. All rights reserved.