On detection of the number of signals when the noise covariance matrix is arbitrary

Journal of Multivariate Analysis

Volumn 20, Issue 1, 1986, Pages 26-49

  Zhao, L C ^a   Krishnaiah, P R ^a   Bai, Z D ^a  

^a UNIVERSITY OF PITTSBURGH   (United States)

Author keywords

colored noise; determination of rank; information theoretic criteria; model selection; multivariate random effects model and signal detection

Indexed keywords

EID: 46149130406     PISSN: 0047259X     EISSN: 10957243     Source Type: Journal    
DOI: 10.1016/0047-259X(86)90018-7     Document Type: Article

References (20)

1. Information theory and an extension of the maximum likelihood principle
2. Estimating linear statistical relationships
3. Components of variance in MANOVA
4. Asymptotic joint distributions of functions of the eigenvalues of some random matrices for nonnormal populations
5. Some recent developments on complex multivariate distributions
6. Computations of some multivariate distributions
7. Data adaptive principal component signal processing
8. Passive sonar: Fitting models to multiple time series
9. Latent roots and matrix variates A review of some asymptotic results
10. Likelihood ratio tests for relationship between two covariance matrices
11. Modeling by shortest data description
12. Multiple emitter location and signal parameter estimation
13. A multivariate one-way classification model with random effects
14. Estimating the dimension of aodel
15. Data-adaptive detection of a weak signal
16. Determination of the number of signals by information theoretic criteria
17. Spatio-temporal spectral analysis by eigenstructure methods
18. The multivariate distribution of complex normal variables
19. On detection of the number of signals in presence of white noise