The Semiparametric Normal Variance‐Mean Mixture Model (Q4516150)
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 1535879
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | The Semiparametric Normal Variance‐Mean Mixture Model |
scientific article; zbMATH DE number 1535879 |
Statements
The Semiparametric Normal Variance‐Mean Mixture Model (English)
0 references
27 November 2000
0 references
normal mixture
0 references
identification
0 references
consistency
0 references
asymptotic normality
0 references
efficiency
0 references
mixing distribution estimation
0 references
0.8604797720909119
0 references
0.8144984841346741
0 references
0.8074771761894226
0 references
0.797581136226654
0 references
0.7970069050788879
0 references
An i.i.d. sample \(X_1\),\dots, \(X_n\) is considered with PDF \[ p(x;(\alpha,\beta),G)=\int_0^\infty \varphi(x;\alpha+\beta/z,1/z)G(dz), \] where \(\varphi(x;a,s)\) is the normal density with mean \(a\) and variance \(s\), and \(\vartheta=(\alpha,\beta)\) is an unknown parameter, and \(G\) is an unknown mixing distribution. The author considers the problem of \(\vartheta\) and \(G\) estimation. Conditions of identification (unambiguous definiteness of \(\vartheta\) and \(G\) by the data distribution) are given. A semiparametric MLE is constructed and its consistency is demonstrated. Asymptotic normality of some improved estimator and its (nonparametric) efficiency are proven.
0 references
