STOCHASTIC-MODELS FOR CHARACTERIZATION AND PREDICTION OF TIME-SERIES WITH LONG-RANGE DEPENDENCE AND FRACTALITY

Authors
ANH V LUNNEY K PEIRIS S
Citation
V. Anh et al., STOCHASTIC-MODELS FOR CHARACTERIZATION AND PREDICTION OF TIME-SERIES WITH LONG-RANGE DEPENDENCE AND FRACTALITY, Environmental Modelling & Software with Environment Data News, 12(1), 1997, pp. 67-73
Citations number
11
Categorie Soggetti
Computer Application, Chemistry & Engineering","Computer Science Software Graphycs Programming","Engineering, Environmental","Computer Science Interdisciplinary Applications
Journal title
Environmental Modelling & Software with Environment Data News → ACNP
ISSN journal
13648152
Volume
12
Issue
1
Year of publication
1997
Pages
67 - 73
Database
ISI
SICI code
1364-8152(1997)12:1<67:SFCAPO>2.0.ZU;2-G
Abstract
Time series from various fields, such as geophysics, meteorology, hydr ology, air pollution, often display long-range dependence and small-sc ale behaviour (fractality). This paper develops a new class of stochas tic models to represent such properties. An efficient estimation proce dure is described and tested on two concentration time series collecte d in an environmental wind tunnel. These time series simulate two diff erent types of odour sources and possess quite different statistical p roperties that are well described by the new model. (C) 1997 Elsevier Science Ltd.