Convolution-invariant subclasses of generalized hyperbolic distributions
Author
Summary, in English
It is rigorously shown that the generalized Laplace distributions and the normal inverse Gaussian distributions are the only subclasses of the generalized hyperbolic distributions that are closed under convolution. The result is obtained by showing that the corresponding two classes of variance mixing distributionsgamma and inverse Gaussianare the only convolution-invariant classes of the generalized inverse Gaussian distributions.
Department/s
Publishing year
2016
Language
English
Pages
98-103
Publication/Series
Communications in Statistics: Theory and Methods
Volume
45
Issue
1
Document type
Journal article
Publisher
Marcel Dekker
Topic
- Probability Theory and Statistics
Keywords
- Bessel function distribution
- Gamma variance normal mixture
- Generalized
- inverse Gaussian distribution
- Generalized asymmetric Laplace
- distribution
- Inverse gamma distribution
- Variance-mean normal mixture
Status
Published
ISBN/ISSN/Other
- ISSN: 0361-0926