Asymptotic properties of one-step M-estimators Full article
| Journal |
Communications in Statistics - Theory and Methods
ISSN: 0361-0926 , E-ISSN: 1532-415X |
||||
|---|---|---|---|---|---|
| Output data | Year: 2019, Volume: 48, Number: 16, Pages: 4096-4118 Pages count : 23 DOI: 10.1080/03610926.2018.1487982 | ||||
| Tags | asymptotic normality; initial estimator; nonlinear regression; One-step M-estimator | ||||
| Authors |
|
||||
| Affiliations |
|
Abstract:
We study the asymptotic behavior of one-step M-estimators based on not necessarily independent identically distributed observations. In particular, we find conditions for asymptotic normality of these estimators. Asymptotic normality of one-step M-estimators is proven under a wide spectrum of constraints on the exactness of initial estimators. We discuss the question of minimal restrictions on the exactness of initial estimators. We also discuss the asymptotic behavior of the solution to an M-equation closest to the parameter under consideration. As an application, we consider some examples of one-step approximation of quasi-likelihood estimators in nonlinear regression. © 2018, © 2018 Taylor & Francis Group, LLC.
Cite:
Linke Y.
Asymptotic properties of one-step M-estimators
Communications in Statistics - Theory and Methods. 2019. V.48. N16. P.4096-4118. DOI: 10.1080/03610926.2018.1487982 WOS Scopus OpenAlex
Asymptotic properties of one-step M-estimators
Communications in Statistics - Theory and Methods. 2019. V.48. N16. P.4096-4118. DOI: 10.1080/03610926.2018.1487982 WOS Scopus OpenAlex
Identifiers:
| Web of science: | WOS:000473519800011 |
| Scopus: | 2-s2.0-85057328032 |
| OpenAlex: | W2900117068 |