Multivariate Bayesian function estimation

被引:8
作者
Angers, JF [1 ]
Kim, PT
机构
[1] Univ Montreal, Dept Math & Stat, Montreal, PQ H3C 3J7, Canada
[2] Univ Guelph, Dept Math & Stat, Guelph, ON N1G 2W1, Canada
关键词
Bayes factor; comets; cross-validation; eigenfunctions; eigenvalues; posterior; Sobolev spaces; Zeta function;
D O I
10.1214/009053605000000705
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Bayesian methods are developed for the multivariate nonparametric regression problem where the domain is taken to be a compact Riemannian manifold. In terms of the latter, the underlying geometry of the manifold induces certain symmetries on the multivariate nonparametric regression function. The Bayesian approach then allows one to incorporate hierarchical Bayesian methods directly into the spectral structure, thus providing a symmetry-adaptive multivariate Bayesian function estimator. One can also diffuse away some prior information in which the limiting case is a smoothing spline on the manifold. This, together with the result that the smoothing spline solution obtains the minimax rate of convergence in the multivariate nonparametric regression problem, provides good frequentist properties for the Bayes estimators. An application to astronomy is included.
引用
收藏
页码:2967 / 2999
页数:33
相关论文
共 49 条
[1]   HIERARCHICAL BAYESIAN CURVE FITTING AND SMOOTHING [J].
ANGERS, JF ;
DELAMPADY, M .
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1992, 20 (01) :35-49
[2]  
ANGERS JF, 2001, SANKHYA SER A, V63, P287
[3]  
ANGERS JF, 1997, SANKHYA SER B, V59, P28
[4]  
[Anonymous], CATALOGUE COMETARY O
[5]  
[Anonymous], EIGENVALUES RIEMANNI
[6]   EXPONENTIAL MODELS FOR DIRECTIONAL DATA [J].
BERAN, R .
ANNALS OF STATISTICS, 1979, 7 (06) :1162-1178
[7]   TESTING FOR UNIFORMITY ON A COMPACT HOMOGENEOUS SPACE [J].
BERAN, RJ .
JOURNAL OF APPLIED PROBABILITY, 1968, 5 (01) :177-&
[8]  
BERGER J. O., 1985, Springer Series in Statistics, DOI DOI 10.1007/978-1-4757-4286-2
[9]   A test of uniformity on shape spaces [J].
Chikuse, Y ;
Jupp, PE .
JOURNAL OF MULTIVARIATE ANALYSIS, 2004, 88 (01) :163-176
[10]  
Chikuse Y., 2003, STAT SPECIAL MANIFOL, DOI DOI 10.1007/978-0-387-21540-2