Cross-validation of multiway component models
Journal of ChemometricsPublished 1 September 1999
D.J. Louwerse, Age K. Smilde, Henk A. L. Kiers
Citations60
SJR quartileQ3
SJR score0.39
SNIP0.83
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
Two cross-validation methods are presented for multiway component models. They are used for choosing thenumbers of components to use in Tucker3 models describing three-way data. The approach is general and caneasily be adapted to other three-way and multiway models. A model is estimated after leaving out a small part ofthe multiway data array. The predictive residual error sum of squares (PRESS) is calculated for the eliminatedpart of the data by comparing the model values with the actual data. PRESS of the entire data set can becalculated like this sequentially. The methods are the leave-bar-out cross-validation method, which leaves outdata slices in all modes, and the EM cross-validation method, which handles eliminated data as missing values. Amethod to calculate the statistical significance of the PRESS reduction for an additional component, the so calledW-statistic, is provided for Tucker3 models. A strategy is proposed to search along an efficient path, to reducecomputation time, since the number of feasible models as a function of the total number of components summedover the modes increases fast. Copyright 1999 John Wiley & Sons, Ltd.KEY WORDS: cross-validation; three-way models; Tucker3; PARAFAC; PRESS
Keywords
Mathematics
Journal of the American Statistical AssociationStatistical Analysis With Missing Data
17,489 Citations1989Maureen Lahiff, Roderick J. A. Little +1 more
PsychometrikaSome Mathematical Notes on Three-Mode Factor Analysis
4,269 Citations1966Ledyard R Tucker
The model for three-mode factor analysis is discussed in terms of newer applications of mathematical processes including a type of matrix process termed the Kronecker product and the definition of combination variables.
TechnometricsCross-Validatory Estimation of the Number of Components in Factor and Principal Components Models
2,496 Citations1978Svante Wold
AIChE JournalMonitoring batch processes using multiway principal component analysis
1,479 Citations1994Paul Nomikos, John F. MacGregor
The approach is contrasted with other approaches which use theoretical or knowledge-based models, and its potential is illustrated using a detailed simulation study of a semibatch reactor for the production of styrene-butadiene latex.
TechnometricsMultivariate SPC Charts for Monitoring Batch Processes
1,380 Citations1995Paul Nomikos, John F. MacGregor
The problem of using time-varying trajectory data measured on many process variables over the finite duration of a batch process is considered and multiway principal-component analysis is used to compress the information contained in the data trajectories into low-dimensional spaces that describe the operation of past batches.
Journal of ChemometricsMulti‐way principal components‐and PLS‐analysis
742 Citations1987Svante Wold, Paul Geladi +2 more
PsychometrikaPrincipal Component Analysis of Three-Mode Data by Means of Alternating Least Squares Algorithms
728 Citations1980Pieter M. Kroonenberg, Jan de Leeuw
TechnometricsCross-Validatory Choice of the Number of Components From a Principal Component Analysis
364 Citations1982Henry T. Eastment, W. J. Krzanowski
The method is based on successively predicting each element in the data matrix after deleting the corresponding row and column of the matrix, and makes use of recently published algorithms for updating a singular value decomposition.
Leiden Repository (Leiden University)Three-mode principal component analysis : theory and applications
290 Citations1983Pieter M. Kroonenberg
Journal of ChemometricsSelection of optimal regression models via cross‐validation
272 Citations1988David W. Osten
The question of how many regression terms to include in the final model must be addressed, wherever a feature selection procedure, or when a data compression approach is used.
Industrial & Engineering Chemistry ResearchImproved Process Understanding Using Multiway Principal Component Analysis
217 Citations1996Karlene A. Kosanovich, Kenneth Dahl +1 more
It is shown that multiway principal component analysis (MPCA) can be used to identify major sources of variability in the processing steps and correlations between the variations in theprocessing steps and the final product properties are found, and recommendations to reduce the sources of variations are discussed.
Chemometrics and Intelligent Laboratory SystemsPrincipal component analysis of multivariate images
185 Citations1989Paul Geladi, Hans Isaksson +3 more
The method aspires to make maximal use of the possibilities of standard image analysis equipment and to combine the results obtained with more traditional image analysis techniques.
Statistical ScienceMultilinear Models: Applications in Spectroscopy
145 Citations1992Sue E. Leurgans, R. Ross
A unified description of the multilinear models in an array notation is presented, showing how to interpret one initialization of the nonlinear least- squares fits of these models.
Journal of ChemometricsTensorial calibration: II. Second‐order calibration
122 Citations1988Eugenio Sanchez, Bruce R. Kowalski
The generalized rank annihilation method (GRAM) is described from the tensorial perspective, and it is shown that GRAM is equivalent to finding a second‐order tensorial base that spans both tensors (calibration and unknown) with respective diagonal component matrices.
Analytical ChemistryMulticomponent Determination of Chlorinated Hydrocarbons Using a Reaction-Based Chemical Sensor. 3. Medium-Rank Second-Order Calibration with Restricted Tucker Models
89 Citations1994Age K. Smilde, Romá Tauler +3 more
Journal of ChemometricsTheory of medium‐rank second‐order calibration with restricted‐Tucker models
86 Citations1994Age K. Smilde, Yongdong Wang +1 more
A medium‐rank second‐order calibration method is proposed based on least‐squares restricted Tucker models with the ability to analyze for analytes of interest in a mixture which contains unknown interferences.
Journal of ChemometricsRegression on multivariate images: Principal component regression for modeling, prediction and visual diagnostic tools
79 Citations1991Paul Geladi, Kim H. Esbensen
This paper describes the use of principal component regression (PCR) and both model building and prediction are presented for continuous Y‐variables, to supply new image material that can be used for visual inspection on a screen.
Journal of ChemometricsThree‐way methods for the calibration of chromatographic systems: Comparing PARAFAC and three‐way PLS
73 Citations1991Age K. Smilde, D.A. Doornbos
Journal of ChemometricsConstrained three-mode factor analysis as a tool for parameter estimation with second-order instrumental data
58 Citations1998Henk A. L. Kiers, Age K. Smilde
Chemometrics and Intelligent Laboratory SystemsEnzymatic browning of vegetables. Calibration and analysis of variance by multiway methods
57 Citations1996Rasmus Bro, Hanne Heimdal
Journal of Chromatography AThree-mode factor analysis of data on retention in normal-phase high-performance liquid chromatography
34 Citations1984C.L. De Ligny, M.C. Spanjer +2 more
Analytica Chimica ActaMultivariate calibration of reversed-phase chromatographic systems. Some designs based on three-way data analysis
16 Citations1990Age K. Smilde, Piet Hein van der Graaf +3 more
Models that describe the systematic variation in this training set sufficiently, can be used to calibrate a new stationary phase and two models are tested: three-way partial least squares and parallel factor analysis.