Premium
COMPONENTS OF PREDICTION ERRORS FOR A STATIONARY PROCESS WITH ESTIMATED PARAMETERS
Author(s) -
Fotopoulos S. B.,
Ray W. D.
Publication year - 1983
Publication title -
journal of time series analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.576
H-Index - 54
eISSN - 1467-9892
pISSN - 0143-9782
DOI - 10.1111/j.1467-9892.1983.tb00352.x
Subject(s) - mathematics , autoregressive model , series (stratigraphy) , kronecker delta , class (philosophy) , statistics , econometrics , algorithm , artificial intelligence , computer science , paleontology , physics , quantum mechanics , biology
. An alternative approach to the estimation of prediction error using linear time series models, whose parameters are also estimated, is presented. Recurrence relationships are given which are rather less unwieldy operationally than the Kronecker matrix forms used by Yamamoto and Reinsel. We extend somewhat the class of models to other than the purely finite autoregressive models studied by these authors.