Presentation 2006-03-21
Relation Between Prediction Accuracy of Nonlinear Modeling and Nonlinearity of Time Series
Daisuke HARAKI, Tomoya SUZUKI, Tohru IKEGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To analyze time series derived from complex systems, several time-series analysis or its prediction methods have been proposed. n the methods, we usually use a normalized root mean square error to evaluate the prediction accuracy. This measure is suitable to evaluate the error between a true point and a predicted point directly. On the other hand, it is also important to predict a region, not as a point, where the future point is included such as forecast of temporal evolution of typhoons. Conventionally, the prediction region was produced by an ensemble prediction, which estimates temporal evolution of an ensemble from several initial values. In this study, we compared the performance of the ensemble prediction and the bootstrap method on the basis of accuracy or efficiency of estimated prediction regions. By several numerical simulations, we reveal advantages of the bootstrap method for nonlinear time series prediction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Nonlinear time series analysis / local linear prediction / the bootstrap method
Paper # NLP2005-158
Date of Issue

Conference Information
Committee NLP
Conference Date 2006/3/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Relation Between Prediction Accuracy of Nonlinear Modeling and Nonlinearity of Time Series
Sub Title (in English)
Keyword(1) Nonlinear time series analysis
Keyword(2) local linear prediction
Keyword(3) the bootstrap method
1st Author's Name Daisuke HARAKI
1st Author's Affiliation Graduate School of Science and Engineering, Saitama University()
2nd Author's Name Tomoya SUZUKI
2nd Author's Affiliation Department of Electronic Engineering
3rd Author's Name Tohru IKEGUCHI
3rd Author's Affiliation Graduate School of Science and Engineering, Saitama University
Date 2006-03-21
Paper # NLP2005-158
Volume (vol) vol.105
Number (no) 676
Page pp.pp.-
#Pages 6
Date of Issue