Change search
ReferencesLink to record
Permanent link

Direct link
Efficient Bayesian Multivariate Surface Regression
Stockholm University, Sweden .
Linköping University, Department of Computer and Information Science, Statistics. Linköping University, Faculty of Arts and Sciences.
2013 (English)In: Scandinavian Journal of Statistics, ISSN 0303-6898, E-ISSN 1467-9469, Vol. 40, no 4, 706-723 p.Article in journal (Refereed) Published
Abstract [en]

Methods for choosing a fixed set of knot locations in additive spline models are fairly well established in the statistical literature. The curse of dimensionality makes it nontrivial to extend these methods to nonadditive surface models, especially when there are more than a couple of covariates. We propose a multivariate Gaussian surface regression model that combines both additive splines and interactive splines, and a highly efficient Markov chain Monte Carlo algorithm that updates all the knot locations jointly. We use shrinkage prior to avoid overfitting with different estimated shrinkage factors for the additive and surface part of the model, and also different shrinkage parameters for the different response variables. Simulated data and an application to firm leverage data show that the approach is computationally efficient, and that allowing for freely estimated knot locations can offer a substantial improvement in out-of-sample predictive performance.

Place, publisher, year, edition, pages
Wiley-Blackwell , 2013. Vol. 40, no 4, 706-723 p.
Keyword [en]
Bayesian inference, free knots, Markov chain Monte Carlo, surface regression, splines
National Category
Social Sciences
URN: urn:nbn:se:liu:diva-102491DOI: 10.1111/sjos.12022ISI: 000327258100004OAI: diva2:679195
Available from: 2013-12-13 Created: 2013-12-12 Last updated: 2013-12-28

Open Access in DiVA

fulltext(12137 kB)162 downloads
File information
File name FULLTEXT01.pdfFile size 12137 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Villani, Mattias
By organisation
StatisticsFaculty of Arts and Sciences
In the same journal
Scandinavian Journal of Statistics
Social Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 162 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 39 hits
ReferencesLink to record
Permanent link

Direct link