Diagnósticos de Regresión Usando la FDR (Tasa de Descubrimientos Falsos)
We use False Discovery Rate (FDR) tests instead of traditional cutoff values used in regression diagnostics to detect suspicious observations and control the rate of false discoveries. This method reduces the complexity of diagnostics by reducing the set of data points to be considered for further an...
- Autores:
-
Correa, Juan Carlos
- Tipo de recurso:
- Fecha de publicación:
- 2010
- Institución:
- Universidad Santo Tomás
- Repositorio:
- Repositorio Institucional USTA
- Idioma:
- spa
- OAI Identifier:
- oai:repository.usta.edu.co:11634/39532
- Acceso en línea:
- https://revistas.usantotomas.edu.co/index.php/estadistica/article/view/22
http://hdl.handle.net/11634/39532
- Palabra clave:
- FDR
diagnósticos de regresión
pruebas múltiples
- Rights
- License
- http://purl.org/coar/access_right/c_abf2
| Summary: | We use False Discovery Rate (FDR) tests instead of traditional cutoff values used in regression diagnostics to detect suspicious observations and control the rate of false discoveries. This method reduces the complexity of diagnostics by reducing the set of data points to be considered for further analysis, keeping only those that are really extraneous. |
|---|