Activity Number:
|
70
- Nonlinearites and Information
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Business and Economic Statistics Section
|
Abstract #330410
|
|
Title:
|
Bootstrap Procedures for Detecting Multiple Persistence Shifts in a Heteroskedastic Time Series
|
Author(s):
|
Mohitosh Kejriwal* and Xuewen Yu
|
Companies:
|
Purdue University and Purdue University
|
Keywords:
|
heteroskedasticity;
multiple structural changes;
sequential procedure;
unit root;
Wald tests;
wild bootstrap
|
Abstract:
|
This paper proposes new bootstrap procedures for detecting multiple persistence shifts in a time series driven by nonstationary volatility. The assumed volatility process is considerably general in that it can accommodate deterministic shifts including smooth transition variation or discrete breaks, stochastic volatility with jumps, continuous autoregressive stochastic volatility as well as explosive volatility processes. We develop wild bootstrap sup-Wald tests of the null hypothesis that the process is either stationary or has a unit root throughout the sample. The asymptotic validity of the tests is established under the null as well as general persistence change alternatives. We also propose and justify an approach to estimate the number of persistence shifts based on sequential application of the bootstrap tests. An extensive set of Monte Carlo experiments illustrates that the procedures maintain adequate size while exhibiting substantial power against a variety of data generating processes characterized by persistence shifts and heteroskedasticity.
|
Authors who are presenting talks have a * after their name.