Estimation and Forecasting of Locally Stationary Processes
Article first published online: 20 NOV 2011
Copyright © 2011 John Wiley & Sons, Ltd.
Journal of Forecasting
Volume 32, Issue 1, pages 86–96, January 2013
How to Cite
Palma, W., Olea, R. and Ferreira, G. (2013), Estimation and Forecasting of Locally Stationary Processes. J. Forecast., 32: 86–96. doi: 10.1002/for.1259
- Issue published online: 26 DEC 2012
- Article first published online: 20 NOV 2011
- Kalman filter;
- state space system;
- long-range dependence;
- local stationarity;
- time-varying models
This paper develops a state space framework for the statistical analysis of a class of locally stationary processes. The proposed Kalman filter approach provides a numerically efficient methodology for estimating and predicting locally stationary models and allows for the handling of missing values. It provides both exact and approximate maximum likelihood estimates. Furthermore, as suggested by the Monte Carlo simulations reported in this work, the performance of the proposed methodology is very good, even for relatively small sample sizes. Copyright © 2011 John Wiley & Sons, Ltd.