Comparison of selection methods of explanatory variables in PLS regression with application to manufacturing process data

Chemometrics and Intelligent Laboratory Systems

Volumn 58, Issue 2, 2001, Pages 171-193

  Gauchi, Jean Pierre ^a   Chagnon, Pierre ^b  

^a CEMAGREF   (France)

^b Rhodia Recherches   (France)

Author keywords

Industrial processes; PLS regression; Variable selection method

Indexed keywords

CHEMICAL INDUSTRY; CONFERENCE PAPER; FOOD INDUSTRY; INTERMETHOD COMPARISON; OIL INDUSTRY; PREDICTION; PRIORITY JOURNAL; REGRESSION ANALYSIS; STATISTICAL MODEL;

EID: 0035965455     PISSN: 01697439     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0169-7439(01)00158-7     Document Type: Conference Paper

References (23)

1. Predictive ability of regression models: Part II. Selection of the best predictive PLS model
2. Genetic algorithms and their statistical applications: An introduction
3. Regressions by leaps and bounds
4. Utilisation de la régression PLS pour l'analyse des plans d'expériences en chimie de formulation
5. A predictive approach to the random effect model
6. The PLS multivariate regression model: Testing the significance of successive PLS components
7. Genetic algorithms as a strategy for feature selection
8. Modélisation du procédé de fabrication d']un antibiotique par régression PLS, explication et prédiction
9. Interactive variable selection (IVS) for PLS: Part I. Theory and algorithms
10. Interactive variable selection (IVS) for PLS: Part II. Chemical application
11. Multi-way partial least squares in monitoring batch processes
12. A quantitative structure-activity relationship study of some substance P-related peptides - A multivariate approach using PLS and variable selection
13. Application of genetic function approximation to quantitative structure-activity relationships and quantitative structure-property relationships
14. A fast algorithm for variable selection in the normal linear model
15. Cross-validatory choice and assessment of statistical predictions
16. Improvement of PLS model transferability by robust wavelength selection