- Title
- MaxEnt alternatives to pearson family distributions
- Creator
- Stokes, Barrie J.
- Relation
- 31st International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering. AIP Conference Proceedings: 31st International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (Waterloo, Canada 9-16 July, 2011) p. 250-259
- Publisher Link
- http://dx.doi.org/10.1063/1.3703642
- Publisher
- American Institute of Physics
- Resource Type
- conference paper
- Date
- 2012
- Description
- In a previous MaxEnt conference [11] a method of obtaining MaxEnt univariate distributions under a variety of constraints was presented. The Mathematica function Interpolation [], normally used with numerical data, can also process "semi-symbolic" data, and Lagrange Multiplier equations were solved for a set of symbolic ordinates describing the required MaxEnt probability density function. We apply a more developed version of this approach to finding MaxEnt distributions having prescribed β1 and β2 values, and compare the entropy of the MaxEnt distribution to that of the Pearson family distribution having the same β1 and β2. These MaxEnt distributions do have, in general, greater entropy than the related Pearson distribution. In accordance with Jaynes' Maximum Entropy Principle, these MaxEnt distributions are thus to be preferred to the corresponding Pearson distributions as priors in Bayes' Theorem.
- Subject
- maximum entropy distributions; Pearson distributions; mathematica
- Identifier
- http://hdl.handle.net/1959.13/1051411
- Identifier
- uon:15284
- Identifier
- ISBN:9780735410398
- Rights
- © American Institute of Physics
- Language
- eng
- Full Text
- Reviewed
- Hits: 956
- Visitors: 1326
- Downloads: 395
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | ATTACHMENT01 | Publisher version (open access) | 1 MB | Adobe Acrobat PDF | View Details Download |