We propose a new non-convex penalty in linear regression models. The new penalty function can be considered a competitor of the LASSO, SCAD or MCP penalties, as it guarantees sparse variable selection while reducing bias for the non-null estimates. We introduce the methodology and present some comparisons among different approaches.
Daniele Cuntrera, Vito Muggeo, Luigi Augugliaro (2022). Variable Selection with Quasi-Unbiased Estimation: the CDF Penalty. In Proceedings of the 36th International Workshop on Statistical Modelling (pp. 144-149).
Variable Selection with Quasi-Unbiased Estimation: the CDF Penalty
Daniele Cuntrera
;Vito Muggeo;Luigi Augugliaro
2022-07-01
Abstract
We propose a new non-convex penalty in linear regression models. The new penalty function can be considered a competitor of the LASSO, SCAD or MCP penalties, as it guarantees sparse variable selection while reducing bias for the non-null estimates. We introduce the methodology and present some comparisons among different approaches.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Proceedings_IWSM_36_Trieste_2022-145-150.pdf
Solo gestori archvio
Descrizione: Contributo completo
Tipologia:
Versione Editoriale
Dimensione
931 kB
Formato
Adobe PDF
|
931 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
