Nonparametric regression using linear combinations of basis functions

Authors:
Robert Kohn;Michael Smith;David Chan
Affiliations:
Australian Graduate School of Management, University of New South Wales, Sydney 2052, Australia;Econometrics and Business Statistics Group, Faculty of Economics and Business, University of Sydney, NSW 2006, Australia;Australian Graduate School of Management, University of New South Wales, Sydney 2052, Australia
Venue:
Statistics and Computing
Year:
2001

Citing 2
Cited 12

Radial basis functions for multivariable interpolation: a review

Algorithms for approximation
Bayesian radial basis functions of variable dimension

Neural Computation

Efficient sampling schemes for Bayesian MARS models with many predictors

Statistics and Computing
Robust image classification

Signal Processing
Logistic regression using covariates obtained by product-unit neural network models

Pattern Recognition
A general approach to heteroscedastic linear regression

Statistics and Computing
Learning to Recognize Objects with Little Supervision

International Journal of Computer Vision
Predictive performance of Dirichlet process shrinkage methods in linear regression

Computational Statistics & Data Analysis
A statistical approach to the problem of restoring damaged and contaminated images

Pattern Recognition
Bayesian skew selection for multivariate models

Computational Statistics & Data Analysis
Bayesian variable selection and model averaging in the arbitrage pricing theory model

Computational Statistics & Data Analysis
Bayesian variable selection for Gaussian process regression: Application to chemometric calibration of spectrometers

Neurocomputing
A sign based loss approach to model selection in nonparametric regression

Statistics and Computing
Bayesian Generalized Kernel Mixed Models

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses a Bayesian approach to nonparametric regression initially proposed by Smith and Kohn (1996. Journal of Econometrics 75: 317–344). In this approach the regression function is represented as a linear combination of basis terms. The basis terms can be univariate or multivariate functions and can include polynomials, natural splines and radial basis functions. A Bayesian hierarchical model is used such that the coefficient of each basis term can be zero with positive prior probability. The presence of basis terms in the model is determined by latent indicator variables. The posterior mean is estimated by Markov chain Monte Carlo simulation because it is computationally intractable to compute the posterior mean analytically unless a small number of basis terms is used. The present article updates the work of Smith and Kohn (1996. Journal of Econometrics 75: 317–344) to take account of work by us and others over the last three years. A careful discussion is given to all aspects of the model specification, function estimation and the use of sampling schemes. In particular, new sampling schemes are introduced to carry out the variable selection methodology.