|
Activity Number:
|
400
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #300895 |
|
Title:
|
On Optimal Maximum Likelihood Estimation for Locally Stationary Long-Memory Processes
|
|
Author(s):
|
Jan Beran*+
|
|
Companies:
|
University of Konstanz
|
|
Address:
|
Department of Mathematics and Statistics, Konstanz, International, 78457, Germany
|
|
Keywords:
|
long memory ; fractional ARIMA process ; local stationarity ; bandwidth selection ; maximum likelihood estimation
|
|
Abstract:
|
Parameter estimation for time-dependent locally stationary long-memory processes is considered. A limit theorem for a local maximum likelihood estimator is derived. Asymptotic formulas for the mean squared error lead to an asymptotic formula for the optimal bandwidth. Quite surprisingly, local estimation of $d$ turns out to be comparable to regression smoothing with iid residuals in the sense that the optimal bandwidth is of the order $n^{-1/5}$ and inversely proportional to the square of the second derivative of $d$. Several data examples illustrate the method.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2008 program |
