We consider the problem of robust fitting for statistical models applied to multivariate torus data, e.g., data which are multivariate angles. We discuss two different definitions of outliers, “geometric” and “probabilistic” outliers, and the proposed robust methods to cope with them. We mainly focus on multivariate wrapped models together with some computational aspects.
Robust Issues in Estimating Models for Multivariate Torus Data
Giovanni Saraceno;
2021
Abstract
We consider the problem of robust fitting for statistical models applied to multivariate torus data, e.g., data which are multivariate angles. We discuss two different definitions of outliers, “geometric” and “probabilistic” outliers, and the proposed robust methods to cope with them. We mainly focus on multivariate wrapped models together with some computational aspects.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
cladag2021.pdf
accesso aperto
Descrizione: Articolo
Tipologia:
Published (Publisher's Version of Record)
Licenza:
Creative commons
Dimensione
139.72 kB
Formato
Adobe PDF
|
139.72 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
