Optimal estimation for semimartingales (Q3740856)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3976148
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Optimal estimation for semimartingales |
scientific article; zbMATH DE number 3976148 |
Statements
Optimal estimation for semimartingales (English)
0 references
1986
0 references
optimal estimation
0 references
stochastic integrals
0 references
Aalen's model
0 references
Liptser's model
0 references
diffusion processes
0 references
asymptotic normality
0 references
strong consistency
0 references
Godambe's theory of parametric estimation
0 references
semimartingale
0 references
local martingale
0 references
estimating equations
0 references
maximum likelihood
0 references
least squares estimates
0 references
0.8798667788505554
0 references
0.8758711218833923
0 references
0.8452585339546204
0 references
0.8359635472297668
0 references
This paper extends a result of Godambe's theory of parametric estimation for discrete-time stochastic processes to the continuous-time case. Let \({\mathcal P}=\{P\}\) be a family of probability measures such that (\(\Omega\),F,P) is complete, \((F_ t\), \(t\geq 0)\) is a standard filtration, and \(X=(X_ t,F_ t\), \(t\geq 0)\) is a semimartingale for every \(P\in {\mathcal P}\). For a parameter \(\theta\) (P), suppose \(X_ t=V_{t,\theta}+H_{t,\theta}\) where the \(V_{\theta}\) process is predictable and locally of bounded variation and the \(H_{\theta}\) process is a local martingale. Consider estimating equations for \(\theta\) of the form \(\int^{t}_{0}a_{u,\theta} dH_{u,\theta}=0\) where the \(a_{\theta}\) process is predictable. Under regularity conditions, an optimal form for \(a_{\theta}\) in the sense of \textit{V. P. Godambe} [Ann. Math. Stat. 31, 1208-1211 (1960; Zbl 0118.343)] is determined. When \(V_{t,\theta}\) is linear in \(\theta\) the optimal \({\hat \theta}_ t\) corresponds to certain maximum likelihood or least squares estimates derived previously in special cases. Asymptotic properties of \({\hat \theta}_ t\) are discussed.
0 references