Bayesian regression with multivariate linear splines Academic Article

abstract

• Summary We present a Bayesian analysis of a piecewise linear model constructed by using basis functions which generalizes the univariate linear spline to higher dimensions. Prior distributions are adopted on both the number and the locations of the splines, which leads to a model averaging approach to prediction with predictive distributions that take into account model uncertainty. Conditioning on the data produces a Bayes local linear model with distributions on both predictions and local linear parameters. The method is spatially adaptive and covariate selection is achieved by using splines of lower dimension than the data.

authors

• Mallick, Bani

published proceedings

• JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY

altmetric score

• 3

author list (cited authors)

• Holmes, C. C., & Mallick, B. K.

citation count

• 52

complete list of authors

• Holmes, CC||Mallick, BK

publication date

• January 2001

publisher

• Oxford University Press (OUP)  Publisher

keywords

• Bayesian Model Averaging
• Bayesian Piecewise Linear Regression
• Local Linear Regression
• Multivariate Splines
• Non-linear Regression

Digital Object Identifier (DOI)

• 10.1111/1467-9868.00272

start page

• 3

end page

• 17

volume

• 63

issue

• 1

URL

• http%3A%2F%2Fdx.doi.org%2F10.1111%2F1467-9868.00272