论文信息 - A practical procedure to estimate the shape parameter in the generalized Gaussian distribution

A practical procedure to estimate the shape parameter in the generalized Gaussian distribution

We propose a method to estimate the shape parameter p in the generalized Gaussian distribution. Our estimator is an explicit approximate solution to the trascendental estimator obtained by the method of moments. An estimator for p, based on the method of moments, does not always exist, however we show that it is possible to find such an estimator with high probability for most of the practical situations. A numeric-analytical procedure to obtain the confidence intervals for p is also presented. We illustrate our procedures on data obtained from the different subbands of the audio MP3 encoder.

J. A. Domínguez-Molina

[1] I. S. Gradshteyn,et al. Table of Integrals, Series, and Products , 1976 .

[2] I. Olkin. An inequality satisfied by the gamma function , 1958 .

[3] I. M. Pyshik,et al. Table of integrals, series, and products , 1965 .

[4] Franklin A. Graybill,et al. Introduction to The theory , 1974 .

[5] W. R. Schucany,et al. Generating Random Variates Using Transformations with Multiple Roots , 1976 .

[6] J. G. Kalbfleisch. Probability and Statistical Inference , 1977 .

[7] M. Varanasi,et al. Parametric generalized Gaussian density estimation , 1989 .

[8] Alberto Leon-Garcia,et al. Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[9] Jose C. Principe,et al. Minimum entropy algorithms for source separation , 1998, 1998 Midwest Symposium on Circuits and Systems (Cat. No. 98CB36268).

[10] Andrzej Cichocki,et al. Local stability analysis of flexible independent component analysis algorithm , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[11] López Esquivel,et al. Una Metodología de Investigación en la Estimación del Parámetro de Forma de la Distribución Gaussiana Generalizada , 2000 .