Autoregressive modeling is a widespread parametricspectrum estimation method. It is well known that, in the caseof stationary processes with unknown order, its accuracy canbe improved by averaging models of different complexity usingsuitably chosen weights. The paper proposes an extension of thistechnique to the case of multivariate locally stationary processes.The proposed solution is based on local autoregressive modeling,and combines model averaging with estimation bandwidth adap-tation. Results of simulations demonstrate that the application ofthe proposed decision rules allows one to outperform the standardapproach, which does not include the bandwidth adaptation.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.23919/eusipco.2019.8902751
- Category
- Aktywność konferencyjna
- Type
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language
- angielski
- Publication year
- 2019
