On rates of convergence of information theoretic criterion in rank determination of one-way random effects models



In this paper, upper bounds on the probabilities of wrong determination of the rank of covariance matrix of random effects in one-way random effects models are given, based on the information theoretic criterion. Under weak conditions, the bounds are shown of exponential-type.

Key words and phrases

Rate of convergence information theoretic criterion one-way random effects model rank determination 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Anderson, T. W. (1984). Estimation linear statistical relationships,Ann. Statist.,12, 1–45.Google Scholar
  2. Anderson, T. W. (1985). Components of variance in MANOVA,Multivariate Analysis (ed. P. R. Krishnaiah),6, 1–8, North-Holland, Amsterdam.Google Scholar
  3. Bai, Z. D., Krishnaiah, P. R. and Zhao, L. C. (1989). On rate of convergence of efficient detection criteria in signal processing with white noise,IEEE Trans. Inform. Theory,35, 380–388.Google Scholar
  4. Schott, J. R. and Saw, J. G. (1984). A multivariate one-way classification model with random effects,J. Multivariate Anal.,15, 1–12.Google Scholar
  5. Tam, K. W. and Wu, Y. (1991). On the convergence of general information theoretic criteria in signal processing when the covariance matrix is arbitrary,IEEE Trans. Inform. Theory,37, 1667–1671.Google Scholar
  6. Zhao, L. C., Krishnaiah, P. R. and Bai, Z. D. (1986). On detection of the number of signals when the noise covariance matrix is arbitrary,J. Multivariate Anal.,20, 26–48.Google Scholar

Copyright information

© The Institute of Statistical Mathematics 1993

Authors and Affiliations

  • Y. Wu
    • 1
  1. 1.Department of Mathematics and StatisticsYork UniversityNorth YorkCanada

Personalised recommendations