Spatially Adaptive Bayesian P-Splines with Heteroscedastic Errors

Ciprian Crainiceanu, David Ruppert and Raymond Carroll
Additional contact information
Ciprian Crainiceanu: Johns Hokins Bloomberg School of Public Health, Department of Biostatistics
David Ruppert: School of Operational Research & Industrial Engineering, Cornell University
Raymond Carroll: Department of Statistics, Texas A&M University

No 1061, Johns Hopkins University Dept. of Biostatistics Working Paper Series from Berkeley Electronic Press

Abstract: An increasingly popular tool for nonparametric smoothing are penalized splines (P-splines) which use low-rank spline bases to make computations tractable while maintaining accuracy as good as smoothing splines. This paper extends penalized spline methodology by both modeling the variance function nonparametrically and using a spatially adaptive smoothing parameter. These extensions have been studied before, but never together and never in the multivariate case. This combination is needed for satisfactory inference and can be implemented effectively by Bayesian \mbox{MCMC}. The variance process controlling the spatially-adaptive shrinkage of the mean and the variance of the heteroscedastic error process are modeled as log-penalized splines. We discuss the choice of priors and extensions of the methodology,in particular, to multivariate smoothing using low-rank thin plate splines. A fully Bayesian approach provides the joint posterior distribution of all parameters, in particular, of the error standard deviation and penalty functions. In the multivariate case we produce maps of the standard deviation and penalty functions. Our methodology can be implemented using the Bayesian software WinBUGS.

Keywords: Knot selection; MCMC; Mixed models; Multivariate smoothing; Spatially adaptive penalty; Thin-plate splines (search for similar items in EconPapers)
Date: 2004-09-27
Note: oai:bepress.com:jhubiostat-1061
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.bepress.com/cgi/viewcontent.cgi?article=1061&context=jhubiostat (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bep:jhubio:1061

Access Statistics for this paper

More papers in Johns Hopkins University Dept. of Biostatistics Working Paper Series from Berkeley Electronic Press
Bibliographic data for series maintained by Christopher F. Baum ().