Compositional data are very common in many disciplines, which consist of vectors of positive values summing to a unit. Several theoretical efforts have been committed to identify outliers in this kind of data. Aim of this work is to propose for compositional data a procedure that is based on median absolute deviation and a correlation median.
Detecting compositional outliers using Comedian Method
DI PALMA, MARIA ANNA;
2013-01-01
Abstract
Compositional data are very common in many disciplines, which consist of vectors of positive values summing to a unit. Several theoretical efforts have been committed to identify outliers in this kind of data. Aim of this work is to propose for compositional data a procedure that is based on median absolute deviation and a correlation median.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
2732-5363-1-PB.pdf
non disponibili
Tipologia:
Abstract
Licenza:
DRM non definito
Dimensione
313.32 kB
Formato
Adobe PDF
|
313.32 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.
