On the use of the observation‐wisek‐fold operation in PCA cross‐validation
- 14 July 2015
- journal article
- research article
- Published by Wiley in Journal of Chemometrics
- Vol. 29 (8) , 467-478
Abstract
Cross‐validation (CV) is a common approach for determining the optimal number of components in a principal component analysis model. To guarantee the independence between model testing and calibration, the observation‐wisek‐fold operation is commonly implemented in each cross‐validation step. This operation renders the CV algorithm computationally intensive, and it is the main limitation to apply CV on very large data sets. In this paper, we carry out an empirical and theoretical investigation of the use of this operation in the element‐wisek‐fold (ekf) algorithm, the state‐of‐the‐art CV algorithm. We show that when very large data sets need to be cross‐validated and the computational time is a matter of concern, the observation‐wisek‐fold operation can be skipped. The theoretical properties of the resulting modified algorithm, referred to as column‐wisek‐fold (ckf) algorithm, are derived. Also, its performance is evaluated with several artificial and real data sets. We suggest theckfalgorithm to be a valid alternative to the standardekfto reduce the computational time needed to cross‐validate a data set. Copyright © 2015 John Wiley & Sons, Ltd.Keywords
Funding Information
- European commision (305340)
This publication has 36 references indexed in Scilit:
- Simplivariate Models: Uncovering the Underlying Biology in Functional Genomics DataPLOS ONE, 2011
- Common variants at five new loci associated with early-onset inflammatory bowel diseaseNature Genetics, 2009
- The Metabonomic Signature of Celiac DiseaseJournal of Proteome Research, 2008
- Framework for regression‐based missing data imputation methods in on‐line MSPCJournal of Chemometrics, 2005
- Principal Component Analysis2005
- Rapid Spectroscopic Analysis of Marzipan—Comparative InstrumentationJournal of Near Infrared Spectroscopy, 2004
- Dealing with missing data in MSPC: several methods, different interpretations, some examplesJournal of Chemometrics, 2002
- Comparative analysis of statistical pattern recognition methods in high dimensional settingsPattern Recognition, 1994
- Cross-Validatory Choice of the Number of Components From a Principal Component AnalysisTechnometrics, 1982
- Cross-Validatory Estimation of the Number of Components in Factor and Principal Components ModelsTechnometrics, 1978