Computational Statistics (2003) 18:533-546
© Physica-Verlag 2003
Derivation of a State-Space Model by
Functional Data Analysis
Mariano J. Valderrama!, Monica Ortega-Moreno
2
, Pedro Gonzalez
3
and
Ana M. Aguilera
4
Department of Statistics and Operations Research, Faculty
of Pharmacy, University of-Granada. 18071 Granada, Spain.
E-mail: valderra@ugr.es
2 Department of General Economics and Statistics, Faculty of Economics
Sciences, University of Huelva. 21071 Huelva, Spain. E-mail: orteg-
amo@uhu.es
3 Department of Applied Mathematics, School of Civil Engineering,
University of Granada. 18071 Granada, Spain. E-mail: prodelas@ugr.es
4 Department of Statistics and Operations Research, Faculty
of Sciences, University of Granada. 18071 Granada, Spain.
E-mail: aaguiler@ugr.es
Summary
By approximating a stochastic process by means of spline interpolation of
its sample-paths, a time dependent state-space model is introduced. Then
we derive the expression of the associated transition matrix that allows
to obtain a discrete model useful in applications. In order to essay the
behaviour of the proposed models simulations on a narrow-band process
are developed. Finally, the paper includes an application with real data
obtained from the Stock Market of Madrid.
Keywords: Functional PCA; B-spline; state-space model; Kalman filter;
narrow-band process.