Template-Type: ReDIF-Paper 1.0
Title: Analytic convergence rates and parameterisation issues for the  Gibbs
  	sampler applied to state space models
Author-Name: Michael K Pitt
Author-Name: Neil Shephard
Creation-Date: 199604
Abstract: In this paper we obtain a closed form expression for the
  	convergence rate of the Gibbs sampler applied to an AR(1) plus noise
  	model in terms of the parameters of the model. We also provide
  	evidence that a ``centered'' parameterisation of a state space model
  	is preferable for the performance of the Gibbs sampler. These two
  	results provide guidance when the Gaussianity or linearity of the
  	state space form is lost. We illustrate this by examining the
  	performance of a Markov Chain Monte Carlo sampler for the Stochastic
  	Volatility model.
Keywords: Blocking; Convergence rates; Gibbs sampling; Parameterisation;
  	Simulation smoother; Stochastic Volatility.
Series: W
Number: 20 & 113
File-URL: http://www.nuff.ox.ac.uk/economics_wp/w20/conpar.zip
File-Format: Application/postscript/zipped
File-Size: 118,062 bytes
Handle: RePEc:nuf:econwp:0020