Uniform convergence rates and uniform adaptive estimation in mixtures of regressions

Uniform convergence rates and uniform adaptive estimation in mixtures of regressions

In this thesis, we develop theoretical tools to examine estimators in non-parametric regression models in regard of uniform convergence rates and uniform adaptivity with respect to the smoothness of the parameter functions. Subsequently, those are applied to non-parametric regression models with Höl...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Glavni autor: Werner, Heiko
Daljnji autori: Holzmann, Hajo (Prof. Dr.) (Savjetnik disertacije)
Format: Dissertation
Jezik:engleski
Izdano: Philipps-Universität Marburg 2018
Teme:
mixtures of normals
Minimum Kontrast Schätzung
mixtures of regressions
Mischungen von Normalverteilungen
adaptive estimation
non-parametri
Gleichmäßige Konvergenzraten
M-estimation
minimum contrast estimation
Mathematik
M-Schätzung
uniform convergence rates
Adaptive Schätzung
Mischregressionen
Mathematics
Online pristup:PDF cijeli tekst
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!
Opis
Sažetak:In this thesis, we develop theoretical tools to examine estimators in non-parametric regression models in regard of uniform convergence rates and uniform adaptivity with respect to the smoothness of the parameter functions. Subsequently, those are applied to non-parametric regression models with Hölder-smooth parameter functions. One model is a mixture of Gaussian regressions and the other model is a mixture model with two components and an unspecified symmetric error distribution.
Opis fizičkog objekta:166 Seiten
Digitalni identifikator objekta:10.17192/z2019.0100

Slični predmeti