Institute of Mathematical Statistics Collections

Analytic perturbations and systematic bias in statistical modeling and inference

Jerzy A. Filar, Irene Hudson, Thomas Mathew, and Bimal Sinha

Full-text: Open access


In this paper we provide a comprehensive study of statistical inference in linear and allied models which exhibit some analytic perturbations in their design and covariance matrices. We also indicate a few potential applications. In the theory of perturbations of linear operators it has been known for a long time that the so-called “singular perturbations” can have a big impact on solutions of equations involving these operators even when their size is small. It appears that so far the question of whether such undesirable phenomena can also occur in statistical models and their solutions has not been formally studied. The models considered in this article arise in the context of nonlinear models where a single parameter accounts for the nonlinearity.

Chapter information

N. Balakrishnan, Edsel A. Peña and Mervyn J. Silvapulle, eds., Beyond Parametrics in Interdisciplinary Research: Festschrift in Honor of Professor Pranab K. Sen (Beachwood, Ohio, USA: Institute of Mathematical Statistics, 2008), 17-34

First available in Project Euclid: 1 April 2008

Permanent link to this document

Digital Object Identifier

Primary: 15A99: Miscellaneous topics
Secondary: 62J99: None of the above, but in this section

analytic perturbation design matrix eigen vectors eigen values factor analysis nonlinear models principal components robustness

Copyright © 2008, Institute of Mathematical Statistics


Filar, Jerzy A.; Hudson, Irene; Mathew, Thomas; Sinha, Bimal. Analytic perturbations and systematic bias in statistical modeling and inference. Beyond Parametrics in Interdisciplinary Research: Festschrift in Honor of Professor Pranab K. Sen, 17--34, Institute of Mathematical Statistics, Beachwood, Ohio, USA, 2008. doi:10.1214/193940307000000022.

Export citation


  • [1] Anderson, T. W. (1984). An Introduction to Multivariate Statistical Analysis, 2nd ed. Wiley, New York.
  • [2] Avrachenkov, K. E. (1999). Analytic perturbation theory and its applications. Doctoral dissertation, University of South Australia.
  • [3] Avrachenkov, K. E. and Haviv, M. (2003). Perturbation of null spaces with application to the eigenvalue problem and generalized inverses. Linear Algebra Appl. 369 1–25.
  • [4] Avrachenkov, K. E., Haviv, M. and Howlett, P. G. (2001). Inversion of analytic matrix functions that are singular at the origin. SIAM J. Matrix Anal. Appl. 22 1175–1189.
  • [5] Calafiore, G. and Ghaout, L. E. (2001). Robust maximum likelihood estimation in the linear model. Automatica 37 573–580.
  • [6] Chandrasekaran, G. G., Gu, M. and Sayed, A. H. (1998). Parameter estimation in the presence of bounded data uncertainties. SIAM J. Matrix Anal. Appl. 19 235–252.
  • [7] Christensen, R. (2001). Advanced Linear Modeling, 2nd ed. Springer, New York.
  • [8] Gallant, A. R. (1987). Nonlinear Statistical Models. Wiley, New York.
  • [9] Ghaoui, L. E. and Lebret, H. (1997). Robust solutions to least squares problems with uncertain data. SIAM J. Matrix Anal. Appl. 18 1035–1064.
  • [10] Johnson, R. A. and Wichern, D. W. (2002). Applied Multivariate Statistical Analysis, 5th ed. Prentice Hall, New York.
  • [11] Joreskog, K. G. (1967). Some contributions to maximum likelihood factor analysis. Psychometrika 32 443–482.
  • [12] Kariya, T. and Sinha, B. K. (1989). Robustness of Statistical Tests. Academic Press, New York.
  • [13] Kato, T. (1980). Perturbation Theory for Linear Operators, 2nd ed. Springer, New York.