Kybernetika 49 no. 5, 692-704, 2013

Asymptotics for weakly dependent errors-in-variables

Michal Pešta


Linear relations, containing measurement errors in input and output data, are taken into account in this paper. Parameters of these so-called \emph{errors-in-variables} (EIV) models can be estimated by minimizing the \emph{total least squares} (TLS) of the input-output disturbances. Such an estimate is highly non-linear. Moreover in some realistic situations, the errors cannot be considered as independent by nature. \emph{Weakly dependent} ($\alpha$- and $\varphi$-mixing) disturbances, which are not necessarily stationary nor identically distributed, are considered in the EIV model. Asymptotic normality of the TLS estimate is proved under some reasonable stochastic assumptions on the errors. Derived asymptotic properties provide necessary basis for the validity of block-bootstrap procedures.


asymptotic normality, errors-in-variables (EIV), dependent errors, total least squares (TLS)


15A51, 15A52, 62E20, 65F15, 62J99


  1. T. W. Anderson: An Introduction to Multivariate Statistical Analysis. John Wiley and Sons, New York 1958.   CrossRef
  2. P. Billingsley: Convergence of Probability Measures. First edition. John Wiley and Sons, New York 1968.   CrossRef
  3. R. C. Bradley: Basic properties of strong mixing conditions. A survey and some open questions. Probab. Surveys 2 (2005), 107-144.   CrossRef
  4. P. P. Gallo: Consistency of regression estimates when some variables are subject to error. Comm. Statist Theory Methods 11 (1982), 973-983.   CrossRef
  5. P. P. Gallo: Properties of Estimators in Errors-in-Variables Models. Ph.D. Thesis, University of North Carolina, Chapel Hill 1982.   CrossRef
  6. L. J. Gleser: Estimation in a multivariate ``errors in variables'' regression model: Large sample results. Ann. Statist. 9 (1981), 24-44.   CrossRef
  7. G. H. Golub and C. F. Van Loan: An analysis of the total least squares problem. SIAM J. Numer. Anal. 17 (1980), 6, 883-893.   CrossRef
  8. J. D. Healy: Estimation and Tests for Unknown Linear Restrictions in Multivariate Linear Models. Ph.D. Thesis, Purdue University 1975.   CrossRef
  9. N. Herrndorf: A functional central limit theorem for strongly mixing sequence of random variables. Probab. Theory Rel. Fields 69 (1985), 4, 541-550.   CrossRef
  10. I. A. Ibragimov and Y. V. Linnik: Independent and Stationary Sequences of Random Variables. Wolters-Noordhoff 1971.   CrossRef
  11. Z. Lin and C. Lu: Limit Theory for Mixing Dependent Random Variables. Springer-Verlag, New York 1997.   CrossRef
  12. M. Pešta: Strongly consistent estimation in dependent errors-in-variables. Acta Univ. Carolin. - Math. Phys. 52 (2011), 1, 69-79.   CrossRef
  13. M. Pešta: Total least squares and bootstrapping with application in calibration. Statistics: J. Theor. and Appl. Statistics 46 (2013), 5, 966-991.   CrossRef
  14. M. Rosenblatt: Markov Processes: Structure and Asymptotic Behavior. Springer-Verlag, Berlin 1971.   CrossRef
  15. S. A. Utev: The central limit theorem for $\varphi$-mixing arrays of random variables. Theory Prob. Appl. 35 (1990), 131-139.   CrossRef