No label defined (Q3221194)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3888710
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3888710 |
Statements
1983
0 references
density estimation
0 references
mixtures of normal distributions
0 references
gamma normal
0 references
beta
0 references
Dirichlet process
0 references
prior distribution
0 references
choice of the prior parameters
0 references
0.8829025626182556
0 references
0.8766180276870728
0 references
0.8549416661262512
0 references
0.8537111878395081
0 references
0.8495944738388062
0 references
[For the entire collection see Zbl 0517.00012.] For a countable mixture \(f(x)=\sum p_ ih(x| \mu_ i,\sigma_ i)\) of normal distributions h a prior distribution for \(p_ i,\mu_ i,\sigma_ i\) is used with \((p_ 1,p_ 2,.)\) and \((\mu_ 1,\mu_ 2,...,\sigma_ 1,\sigma_ 2,.)\) independent, \((\mu_ 1,\sigma_ 1)\), \((\mu_ 2,\sigma_ 2)..\). i.i.d. gamma normal and \(p_ j=\prod^{j- 1}_{i=1}(1-q_ j)\) with \(q_ 1,q_ 2,..\). i.i.d. beta. The prior can be described as a Dirichlet process. \(E(f(x)| x_ 1,...,x_ n)\) is computed for a sample \(X_ 1,...,X_ n.\) Interpretation of the prior distribution (how much do you trust your prior guess a.o.) and choice of the prior parameters are discussed. Computations are made using a Monte Carlo technique of L. Kuo.
0 references