Asymptotic behavior of M-estimator and related random field for diffusion process (Q756893)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Asymptotic behavior of M-estimator and related random field for diffusion process |
scientific article |
Statements
Asymptotic behavior of M-estimator and related random field for diffusion process (English)
0 references
1990
0 references
A statistical parameter estimation problem in a multidimensional diffusion model of observations is considered. The author investigates the asymptotic behavior of the log-likelihood ratio random fields and of some of more general kind and related ML- and robustified M-estimators, when the observation time goes to infinity and the clean observation data are loaded by additional noises and (or) the true model is misspecified. The results obtained generalize earlier ones on local asymptotic normality, due to \textit{L. LeCam} [Univ. California Publ. Statist. 3, 37- 98 (1960; Zbl 0104.127)] and successors, for noisy, misspecified, and non-ergodic models.
0 references
convergence in distribution
0 references
asymptotic variance
0 references
misspecified models
0 references
maximum likelihood estimation
0 references
multidimensional diffusion model
0 references
log- likelihood ratio random fields
0 references
robustified M-estimators
0 references
local asymptotic normality
0 references
non-ergodic models
0 references
0 references
0 references
