Maximum entropy density estimation from fractional moments

被引:91
作者
Inverardi, PLN [1 ]
Tagliani, A [1 ]
机构
[1] Univ Trent, Fac Econ, Dept Comp & Management Sci, I-38100 Trento, Italy
关键词
entropy; fractional moments; Hankel matrix; maximum entropy; Hausdorff moment problem;
D O I
10.1081/STA-120018189
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
A procedure for the estimation of probability density functions of positive random variables by its fractional moments, is presented. When all the available information is provided by population fractional moments a criterion of choosing fractional moments themselves is detected. When only a sample is known, Jaynes' maximum entropy procedure and the Akaike's estimation procedure are joined together for determining respectively, what and how many sample fractional moments have to be used in the estimation of the density. Some numerical experiments are provided.
引用
收藏
页码:327 / 345
页数:19
相关论文
共 11 条
[1]  
Akaike H., 1973, SECOND INTERNATIONAL, P267
[2]  
[Anonymous], 1992, ENTROPY OPTIMIZATION, DOI DOI 10.1007/978-94-011-2430
[3]   PROBABILITY ESTIMATION AND INFORMATION PRINCIPLES [J].
BAKER, R .
STRUCTURAL SAFETY, 1990, 9 (02) :97-116
[4]   CONVERGENCE OF BEST ENTROPY ESTIMATES [J].
Borwein, J. M. ;
Lewis, A. S. .
SIAM JOURNAL ON OPTIMIZATION, 1991, 1 (02) :191-205
[5]  
BORWEIN JM, 1993, FUND THEOR, V53, P39
[6]   THE MOMENT GENERATING FUNCTION HAS ITS MOMENTS [J].
CRESSIE, N ;
BORKENT, M .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1986, 13 (03) :337-344
[7]   Entropy-convergence in Stieltjes and Hamburger moment problem [J].
Frontini, M ;
Tagliani, A .
APPLIED MATHEMATICS AND COMPUTATION, 1997, 88 (01) :39-51
[8]  
Jaynes E.T., 1979, The maximum entropy principle, P15
[10]  
LIN GD, 1992, SANKHYA SER A, V54, P128