Articles liés à Analysis of Time Series Data in the Presence of Outliers:...

Analysis of Time Series Data in the Presence of Outliers: In frequency domain - Couverture souple

Shittu, Olanrewaju

 
9783844323542: Analysis of Time Series Data in the Presence of Outliers: In frequency domain
Couverture souple
ISBN 10 : 3844323546 ISBN 13 : 9783844323542
Editeur : LAP LAMBERT Academic Publishing, 2011

Synopsis

This book deals with the methods of detection, and identification of outliers in time series data in the frequency domain. It also discusses the method of analysis that would be insensitive to outliers. The author uses some robust regression method to fit sine and cosine coefficients at each Fourier frequency assuming additive outlier (AO) and multiplicative outliers (MO) respectively to obtain discrete Fourier transform for removing outliers from time series data. The parameters of the contaminated series were estimated using the maximum likelihood (ML) method and the statistical properties of the derived estimates were investigated. Two algorithms were proposed for detection and accommodation of aberrant observations in the frequency domain while modified test statistic using a more robust estimate that is resistant to outlier were also developed to test each observation for discordance. A new filtering method of accommodating outliers was also suggested and the performance of various accommodation techniques was determined in respect of the fixed and dynamic models.Real life and simulated data were used to illustrate the techniques.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

This book deals with the methods of detection, and identification of outliers in time series data in the frequency domain. It also discusses the method of analysis that would be insensitive to outliers. The author uses some robust regression method to fit sine and cosine coefficients at each Fourier frequency assuming additive outlier (AO) and multiplicative outliers (MO) respectively to obtain discrete Fourier transform for removing outliers from time series data. The parameters of the contaminated series were estimated using the maximum likelihood (ML) method and the statistical properties of the derived estimates were investigated. Two algorithms were proposed for detection and accommodation of aberrant observations in the frequency domain while modified test statistic using a more robust estimate that is resistant to outlier were also developed to test each observation for discordance. A new filtering method of accommodating outliers was also suggested and the performance of various accommodation techniques was determined in respect of the fixed and dynamic models.Real life and simulated data were used to illustrate the techniques.

Biographie de l'auteur

Dr. O.I. Shittu had B.Sc, M.Sc; M.Phil and Ph.D degrees in statistics from the University of Ibadan, Nigeria. A Chattered Statistician (CStat) and Chattered Scientist (CSci) of the Royal Statistical Society (RSS) London. He also hold an Ordinary Certificate in Statistics awarded by the Institute of Statisticians (IOS) London in 1986

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
LAP LAMBERT Academic Publishing
Date d'édition
2011
Langue
anglais
ISBN 10 
3844323546
ISBN 13 
9783844323542
Reliure
Broché
Nombre de pages
132
Coordonnées du fabricant
non disponible
Personne responsable
KreGa Onlinehandel GmbH
4950000000000
info@krega-onlinehandel.de

Birkenweg 31
Brakel
33034
Allemagne