Exploiting the connection between PLS, Lanczos methods and conjugate gradients: Alternative proofs of some properties of PLS

Journal of Chemometrics

Volumn 16, Issue 7, 2002, Pages 361-367

  Phatak, Aloke ^a   De Hoog, Frank ^a  

^a CSIRO   (Australia)

Author keywords

Biased estimators; Conjugate gradient methods; Lanczos methods; Partial least squares; Principal component regression; Shrinkage

Indexed keywords

EIGENVALUES AND EIGENFUNCTIONS; LEAST SQUARES APPROXIMATIONS; PRINCIPAL COMPONENT ANALYSIS; REGRESSION ANALYSIS; SHRINKAGE;

BIASED ESTIMATORS; CONJUGATE-GRADIENT METHOD; EXTREMAL; LANCZOS' METHODS; LEAST SQUARE REGRESSION METHOD; PARTIAL LEAST SQUARE REGRESSION; PARTIAL LEAST-SQUARES; PRINCIPAL COMPONENT REGRESSION; PRINCIPAL COMPONENTS; PROPERTY;

CONJUGATE GRADIENT METHOD;

ALGORITHM; ANALYTIC METHOD; ARTICLE; CONJUGATE; MATHEMATICAL ANALYSIS; PRINCIPAL COMPONENT ANALYSIS; REGRESSION ANALYSIS;

EID: 0036062572     PISSN: 08869383     EISSN: None     Source Type: Journal    
DOI: 10.1002/cem.728     Document Type: Article

References (25)

1. Calibration modeling by partial least-squares and principal component regression and its optimization using an improved leverage correction for prediction testing
2. Analysis of two partial-least-squares algorithms for multivariate calibration
3. PLS regression methods
4. The collinearity problem in linear regression. The PLS approach to generalized inverses
5. Methods of conjugate gradients for solving linear systems
6. PLS shrinks
7. Partial least squares algorithm yields shrinkage estimators
8. PLS fits closer than PCR
9. On the structure of partial least squares regression
10. SIMPLS an alternative approach to partial least squares regression
11. The rate of convergence of conjugate gradients
12. A statistical view of some chemometrics regression tools
13. The peculiar shrinkage properties of partial least squares regression
14. Shrinkage structure of partial least squares
15. An iteration method for the solution of the eigenvalue problem of linear differential and integral operators
16. Partial least squares regression
17. Comparison of prediction methods for multicollinear data
18. GMRES/CR and Arnoldi/Lanczos as matrix approximation problems
19. The conjugate gradient method and trust regions in large scale optimization
20. A practical termination criterion for the conjugate gradient method