Skip to main content
SpringerLink
Log in

A minimax approach to missing values in linear regression

  • Articles
  • Published:
Statistical Papers Aims and scope Submit manuscript

Abstract

We consider the problem of estimating the parameter vector in the linear model when observations on the independent variables are partially missing or incorrect. A new estimator is developed which systematically combines prior restrictions on the exogenous variables with the incomplete data. We compare this method with the alternative strategy of deleting missing values.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Afifi, A.A., R.M. Elashoff (1966, 1967, 1969a, 1969b), Missing Values in Multivariate Statistics: I.–VI.,Journal of the American Statistical Association 61, 595–604, 62, 10–29, 64, 337–358, 359–365

    Article  MathSciNet  Google Scholar 

  • Anderson, A.B., A. Basilevsky, D.P.J. Hum (1983), Missing Data: A Review of the Literature, in: P.H. Rossi, J.D. Wright, A. Anderson, eds.,Handbook of Survey Research, Academic Press, 415–494

  • Donner, A., B. Rosner (1982), Missing Values Problems in Multiple Linear Regression With Two Independent Variables,Communications in Statistics 11(2), 127–140

    Google Scholar 

  • Drygas, H. (1982), Minimax prediction in linear models, in: W. Klonecki and T. Calinski, eds.,Linear Statistical Inference, Springer-Verlag, New York, 48–60

    Google Scholar 

  • Edgett, G.L. (1956), Multiple Regression With Missing Observations Among the Independent Variables,Journal of the American Statistical Association 51, 122–131

    Article  MathSciNet  Google Scholar 

  • Gaffke, N., B. Heiligers (1989), Bayes, Admissible, and Linear Minimax Estimators in Linear Models with Restricted Parameter Space,Statistics 20, 487–508

    Article  MathSciNet  MATH  Google Scholar 

  • Haitovsky, Y. (1968), Missing Data in Regression Analysis,Journal of the Royal Statistical Society B 30, 67–82

    MATH  Google Scholar 

  • Hering, F., G. Trenkler, P. Stahlecker (1987), Partial Minimax Estimation in Regression Analysis,Statistica Neerlandica 41, nr. 2, 111–128

    Article  MathSciNet  MATH  Google Scholar 

  • Hoffmann, K. (1979), Characterization of linear minimax estimators in linear regression,Mathematische Operationsforschung und Statistik, Series Statistics 10, 19–26

    MathSciNet  MATH  Google Scholar 

  • Hsiao, Cheng (1986),Analysis of Panel Data Cambridge University Press

  • Hübler, O. (1986), Fehlende Werte in linearen Regressionsmodellen,Allgemeines Statistisches Archiv 70, 2/1986, 138–157

    Google Scholar 

  • Intriligator, M.D. (1978),Econometric Models, Techniques, and Applications, New Jersey, Prentice Hall

    MATH  Google Scholar 

  • Judge, G. G., R. C. Hill, W. E. Griffiths, H. Lütkepohl, T.-C. Lee (1988),Introduction to the Theory and Practice of Econometrics, 2nd ed., New York, Wiley

    MATH  Google Scholar 

  • Kuks, J., W. Olman (1972), Minimax linear estimation of regression coefficients II (in Russian),Izv. Akad. Nauk Eston. SSR 21, 66–72

    MathSciNet  MATH  Google Scholar 

  • Läuter, H. (1975), A minimax linear estimator for linear parameters under restrictions in form of inequalities,Mathematische Operationsforschung und Statistik, Series Statistics 6, 689–695

    Google Scholar 

  • Lauterbach J., P. Stahlecker (1988), Approximate Minimax Estimation in Linear Regression: A Simulation Study,Communications in Statistics 17(1), 209–227

    MATH  Google Scholar 

  • Magnus, J. R., H. Neudecker (1988),Matrix Differential Calculus with Applications in Statistics and Econometrics, Wiley, New York

    MATH  Google Scholar 

  • Nijman, T., F. Palm (1988), Efficiency gains due to using missing data procedures in regression models,Statistical Papers 29, 249–256

    Article  MATH  Google Scholar 

  • Pilz, J. (1986), Minimax linear regression estimation with symmetric parameter restriction,Journal of Statistical Planning and Inference 13, 297–318

    Article  MathSciNet  MATH  Google Scholar 

  • Stahlecker, P., M. Jänner, K. Schmidt (1991), Linear-affine Minimax-Schätzer unter Ungleichungsrestriktionen,Allgemeines Statistisches Archiv, 75, 245–264

    Google Scholar 

  • Stahlecker, P., G. Trenkler (1990), Minimax Estimation in Linear Regression with Convex Polyhedral Constraints, Report 90/2—Department of Statistics, University of Dortmund

  • Stahlecker, P., G. Trenkler (1988), Full and partial minimax estimation in regression analysis with additional linear constraints,Linear Algebra Applications 111, 279–292

    Article  MathSciNet  MATH  Google Scholar 

  • Stahlecker, P., J. Lauterbach (1987), Approximate Minimax Estimation in Linear Regression: Theoretical Results,Communications in Statistics 16(4), 1101–1116

    Article  MathSciNet  MATH  Google Scholar 

  • Toutenburg, H. (1982),Prior Information in Linear Models, Wiley, New York

    MATH  Google Scholar 

  • Trenkler, G., P. Stahlecker (1987), Quasi Minimax Estimation in the Linear Regression Model,Statistics 18, 219–226

    Article  MathSciNet  MATH  Google Scholar 

  • Wansbeek, T., A. Kapteyn (1989), Estimation of the error-components model with incomplete panels,Journal of Econometrics 41, 341–361

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut für Statistik und Ökonometrie, Universität Hamburg, von-Melle-Park 5, 20146, Hamburg, F R G

    P. Stahlecker

  2. Institut für VWL, Universität Oldenburg, Postfach 2503, 26111, Oldenburg, F R G

    M. Jänner

Authors
  1. M. Jänner
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. Stahlecker
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Support by Deutsche Forschungsgemeinschaft, Grant No. 284/1-1 is gratefully acknowledged.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Jänner, M., Stahlecker, P. A minimax approach to missing values in linear regression. Statistical Papers 34, 247–261 (1993). https://doi.org/10.1007/BF02925545

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02925545

Linear regression model

Search

Navigation