@article{Ranocha2004,
abstract = {Important characteristics of any algorithm are its complexity and speed in real calculations. From this point of view, we analyze some algorithms for prediction in finite stationary time series. First, we review results developed by P. Bondon [1] and then, we derive the complexities of Levinson and a new algorithm. It is shown that the time needed for real calculations of predictions is proportional to the theoretical complexity of the algorithm. Some practical recommendations for the selection of the best algorithm are given.},
author = {Ranocha, Pavel},
journal = {Kybernetika},
keywords = {stationary time series; multistep prediction; Levinson’s algorithm; innovations algorithm; stationary time series; multistep prediction; Levinson's algorithm; innovations algorithm},
language = {eng},
number = {6},
pages = {[703]-714},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Efficiency of some algorithms for prediction in finite stationary time series},
url = {http://eudml.org/doc/33730},
volume = {40},
year = {2004},
}
TY - JOUR
AU - Ranocha, Pavel
TI - Efficiency of some algorithms for prediction in finite stationary time series
JO - Kybernetika
PY - 2004
PB - Institute of Information Theory and Automation AS CR
VL - 40
IS - 6
SP - [703]
EP - 714
AB - Important characteristics of any algorithm are its complexity and speed in real calculations. From this point of view, we analyze some algorithms for prediction in finite stationary time series. First, we review results developed by P. Bondon [1] and then, we derive the complexities of Levinson and a new algorithm. It is shown that the time needed for real calculations of predictions is proportional to the theoretical complexity of the algorithm. Some practical recommendations for the selection of the best algorithm are given.
LA - eng
KW - stationary time series; multistep prediction; Levinson’s algorithm; innovations algorithm; stationary time series; multistep prediction; Levinson's algorithm; innovations algorithm
UR - http://eudml.org/doc/33730
ER -
