Computing the mean square error of unobserved components extracted by misspecified time series models

Algorithms are presented for computing mean square errors in a misspecified unobserved components model when the true model is known. It is assumed that both the true and misspecified models can be put in linear state space form. The algorithm for filtering is based on the Kalman filter while that f...

Full description

Saved in:
Bibliographic Details
Published inJournal of economic dynamics & control Vol. 33; no. 2; pp. 283 - 295
Main Authors Harvey, Andrew C., Delle Monache, Davide
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 01.02.2009
Elsevier
Elsevier Sequoia S.A
SeriesJournal of Economic Dynamics and Control
Subjects
Algorithms
Average
Computational methods
Detrending
Detrending Exponentially weighted moving average Hodrick-Prescott filter Kalman filter Smoother
Economic models
Error
Exponentially weighted moving average
Hodrick–Prescott filter
Kalman filter
Kalman filters
Mathematical models
Mean square errors
Regression analysis
Smoother
Studies
Time series
Vector-autoregressive models
Detrending
C32
Exponentially weighted moving average
Hodrick–Prescott filter
Kalman filter
Smoother
Online AccessGet full text

Cover

More Information
Summary:Algorithms are presented for computing mean square errors in a misspecified unobserved components model when the true model is known. It is assumed that both the true and misspecified models can be put in linear state space form. The algorithm for filtering is based on the Kalman filter while that for smoothing modifies the fixed-point smoother. Illustrations include the efficiency of the Hodrick–Prescott filter for annual flow data and the mean square error of predictions for misspecified models from the autoregressive integrated moving average class.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0165-1889
1879-1743
DOI:10.1016/j.jedc.2008.05.007