Observability and fisher information matrix in nonlinear regression

Claude Jauffret (1, 2)

1 IM2NP - Institut des Matériaux, de Microélectronique et des Nanosciences de Provence
2 UTLN - Université de Toulon

This paper is devoted to the link between the Fisher Information Matrix invertibility and the observability of a parameter to be estimated in a nonlinear regression problem.

Mots clés: Observability; identifiability; Cramèr-Rao Lower Bound; Fisher Information Matrix; nonlinear regression

Domaines: Théorie [stat.TH]

Claude Jauffret. Observability and fisher information matrix in nonlinear regression. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43 (2), pp.756-759. ⟨10.1109/TAES.2007.4285368⟩. ⟨hal-01820468⟩