| Autor: |
de Jong, Sijmen, Kiers, Henk A.L. |
| Přispěvatelé: |
Psychometrics and Statistics |
| Jazyk: |
angličtina |
| Rok vydání: |
1992 |
| Předmět: |
|
| Zdroj: |
Chemometrics and Intelligent Laboratory Systems, 14(1-3), 155-164. ELSEVIER SCIENCE BV |
| ISSN: |
0169-7439 |
| Popis: |
A method for multivariate regression is proposed that is based on the simultaneous least-squares minimization of Y residuals and X residuals by a number of orthogonal X components. By lending increasing weight to the X variables relative to the Y variables, the procedure moves from ordinary least-squares regression to principal component regression, forming a relatively simple alternative for continuum regression. Analogies and differences with this and other biased regression techniques are discussed. Possible extensions to multi-block problems and nonlinear relationships are indicated. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
