Estimation of spiked eigenvalues in spiked models (Q2884858)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Estimation of spiked eigenvalues in spiked models |
scientific article; zbMATH DE number 6036654
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Estimation of spiked eigenvalues in spiked models |
scientific article; zbMATH DE number 6036654 |
Statements
18 May 2012
0 references
sample covariance matrix
0 references
spiked population model
0 references
estimation
0 references
extreme eigenvalues
0 references
Stieltjes transformation
0 references
consistency
0 references
asymptotic normality
0 references
0 references
0 references
0 references
0 references
Estimation of spiked eigenvalues in spiked models (English)
0 references
The aim of the paper is to estimate the distant spiked eigenvalues of the population covariance matrix without using information of the proper probability distribution (PD). It is shown, that the proposed estimators have the same limiting distributions as those obtained when the PD is known. The estimators are based on the Stieltjes transformation of the empirical probability distribution of the sample. Consistency and asymptotic normality of the new estimators are analysed.
0 references
