Abstract
A time dependent state space model with minimal dimension is introduced in this paper by approximating the stochastic process of continuous time nature by means of spline interpolation of its sample paths and then by differentiating its Karhunen-Loève expansion. A comparative study of forecasting, using the Kalman-Bucy filter, with simulated data is presented from a well known non-stationary process, the Brownian motion, discussing its advantages.
1This research was supported in part by Project No. BFM2000-1466 of Dirección General de Investigación, Ministerio de Ciencia y Tecnología.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ruiz, J.C., Valderrama, M.J., and Gutiérrez, R. (1995). Kalman Filtering on Approximative State Space Models. Journal of Optimization Theory and Applications, 84(2), 415–431.
Valderrama, M.J., Aguilera, A.M. and Ocaña, F.A. (2000). Predicción Dinámica mediante Análisis de Datos Funcionales. Hespérides-La Muralla, Madrid.
Valderrama, M.J., Aguilera, A.M. and Ruiz, J.C. (1998). Time Series Forecasting by Principal Component Methods. In: COMPSTAT98 Proceedings in Computational Statistics, 137–146. Heidelberg: Physica-Verlag.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ortega-Moreno, M., Valderrama, M.J., Ruiz-Molina, J.C. (2002). A State Space Model for Non-Stationary Functional Data1 . In: Härdle, W., Rönz, B. (eds) Compstat. Physica, Heidelberg. https://doi.org/10.1007/978-3-642-57489-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-57489-4_15
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1517-7
Online ISBN: 978-3-642-57489-4
eBook Packages: Springer Book Archive