This research activity deals with robust methods for parameters estimation of nonlinear models and the outliers detection. It specifically discusses some advances in criteria to discriminate among gross errors, bad experimental design, and inadequate model selection. All the methods and the criteria proposed in this work are implemented in BzzMath library, a free scientific tool to solve numerical problems.
Criteria for Outliers Detection in Nonlinear Regression Problems
MANENTI, FLAVIO;
2009-01-01
Abstract
This research activity deals with robust methods for parameters estimation of nonlinear models and the outliers detection. It specifically discusses some advances in criteria to discriminate among gross errors, bad experimental design, and inadequate model selection. All the methods and the criteria proposed in this work are implemented in BzzMath library, a free scientific tool to solve numerical problems.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
ESCAPE19_FULL.pdf
Accesso riservato
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
172.61 kB
Formato
Adobe PDF
|
172.61 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
