Activity Number:
|
353
- Contributed Poster Presentations: Section on Nonparametric Statistics
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract #324350
|
|
Title:
|
A New Nonparametric Estimation Method for multi-fractional Gaussian proces and Its Minimax Properties
|
Author(s):
|
Jinqi Shen* and Tailen Hsing
|
Companies:
|
University of Michigan and University of Michigan
|
Keywords:
|
multi-fractional Gaussian process ;
Nonparametric Method ;
Minimax Property ;
Hurst function ;
Local Polynomial Method ;
Local intransic stationarity
|
Abstract:
|
Estimating multifractional Gaussian process is a hard problem. We develop a new nonparametric method for the estimation of Hurst index function in a multi-fractional Gaussian process. The method is developed from the idea of local intransic stationarity and local polynomial estimator and proper convergence rate is calculated for the situation that we have observations on grids . The minimax rate for the convergence of this problem is calculated and our estimator reaches the minimax rate when dimensions of the domain is not larger than 4.
|
Authors who are presenting talks have a * after their name.