The problem of estimating spectral density of a nonstationary process satisfying local stationarity conditions is considered. The proposed solution is a two step procedure based on local autoregressive (AR) modeling. In the first step Bayesian-like averaging of AR models, differing in order, is performed. The main contribution of the paper is development of a new final-prediction-error-like statistic, which can be used to select optimal estimation bandwidth in the second step of the procedure. Simulation experiments demonstrate that the combined cooperative-competitive approach outperforms the previously introduced fully competitive scheme.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1109/cdc.2017.8264188
- Category
- Aktywność konferencyjna
- Type
- materiały konferencyjne indeksowane w Web of Science
- Language
- angielski
- Publication year
- 2017
