Un nuevo estimador muestral de regresión vía residuos ortogonales derivados del análisis de componentes principales
Regression estimators are tools that employ statistics techniques such as regression analysis in order to gain in efficiency by means of the available auxiliary information. This paper presents the theoretical approach that yields to the proposal of a new orthogonal regression estimator for which the...
- Autores:
-
Rico Bermúdez, Jimmy
- Tipo de recurso:
- Fecha de publicación:
- 2009
- Institución:
- Universidad Santo Tomás
- Repositorio:
- Repositorio Institucional USTA
- Idioma:
- spa
- OAI Identifier:
- oai:repository.usta.edu.co:11634/39556
- Acceso en línea:
- https://revistas.usantotomas.edu.co/index.php/estadistica/article/view/46
http://hdl.handle.net/11634/39556
- Palabra clave:
- Estimador de regresión
información auxiliar
componentes principales
linealización de Taylor
- Rights
- License
- http://purl.org/coar/access_right/c_abf2
| Summary: | Regression estimators are tools that employ statistics techniques such as regression analysis in order to gain in efficiency by means of the available auxiliary information. This paper presents the theoretical approach that yields to the proposal of a new orthogonal regression estimator for which the fit is not based in the theory of classical least squares, but instead, it is based in the theory of principal components which minimizes the orthogonal distances from each point of the scatter plot to the line that incorporates most of the inertia. |
|---|