Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/81920
Authors: 
Giordani, Paolo
Kohn, Robert
Year of Publication: 
2006
Series/Report no.: 
Sveriges Riksbank Working Paper Series 196
Abstract: 
Time series subject to parameter shifts of random magnitude and timing are commonly modeled with a change-point approach using Chib's (1998) algorithm to draw the break dates. We outline some advantages of an alternative approach in which breaks come through mixture distributions in state innovations, and for which the sampler of Gerlach, Carter and Kohn (2000) allows reliable and efficient inference. We show how this approach can be used to (i) model shifts in variance that occur independently of shifts in other parameters (ii) draw the break dates efficiently in change-point and regime-switching models with either Markov or non-Markov transition probabilities. We extend the proofs given in Carter and Kohn (1994) and in Gerlach, Carter and Kohn (2000) to state-space models with system matrices which are functions of lags of the dependent variables, and we further improve the algorithms in Gerlach, Carter and Kohn by introducing to the time series literature the concept of adaptive Metropolis-Hastings sampling for discrete latent variable models. We develop an easily implemented adative algorithm that promises to sizably reduce computing time in a variety of problems including mixture innovation, change-point, regime-switching, and outlier detection.
Subjects: 
Structural breaks
Parameter instability
Change-point
State-space
Mixtures
Discrete latent variables
Adaptive Metropolis-Hastings
JEL: 
C11
C15
C22
Document Type: 
Working Paper

Files in This Item:
File
Size
350.91 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.