The selection of an appropriate sub-set of explanatory variables to use in a linear regression model is an important aspect of a statistical analysis. Classical stepwise regression could be invalidated by a few outling observations. We introduce a robust F-test in order to perform a stepwise regression that is robust against the presence of outliers. The introduced methodology is asymptotically equivalent to the classical one when no contamination is present. Some examples and simulation are presented.
Robust stepwise regression.
Agostinelli, Claudio
2000
Abstract
The selection of an appropriate sub-set of explanatory variables to use in a linear regression model is an important aspect of a statistical analysis. Classical stepwise regression could be invalidated by a few outling observations. We introduce a robust F-test in order to perform a stepwise regression that is robust against the presence of outliers. The introduced methodology is asymptotically equivalent to the classical one when no contamination is present. Some examples and simulation are presented.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
WP_2000_10.pdf
accesso aperto
Licenza:
Non specificato
Dimensione
26.52 MB
Formato
Adobe PDF
|
26.52 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
