Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/220191 
Year of Publication: 
2015
Series/Report no.: 
Discussion Paper No. 102
Publisher: 
Institute for Applied Economic Research (ipea), Brasília
Abstract: 
Space-varying regression models are generalizations of standard linear models where the regression coefficients are allowed to change in space. The spatial structure is specified by a multivariate extension of pairwise difference priors thus enabling incorporation of neighboring structures and easy sampling schemes. Different sampling schemes are available and may be used in an MCMC algorithm. These schemes are compared in terms of chain autocorrelation and resulting inference. We also discuss different prior specifications that accommodate the spatial structure. Results are illustrated with simulated data and applied to a real dataset.
Subjects: 
Bayesian
Hyperparameters
Gibbs sampling
Markov chain Monte Carlo
Markov random fields
Metropolis-Hastings algorithm
Sampling schemes
Document Type: 
Working Paper

Files in This Item:
File
Size
784.15 kB





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