Advertisement

Statistical Papers

, Volume 39, Issue 4, pp 417–421 | Cite as

A note on a result for two SUR models

  • A. K. Gupta
  • D. G. Kabe
Notes
  • 39 Downloads

Abstract

Revankar (1974, p. 190, equation (4.4)) obtains a result for the covariance matrices of the “Aitken” estimators of the regression coefficients parameter matrices of two SUR models. The present note supplies a simpler derivation of this result. It is obtained by using a known result in multivariate statistical analysis, see e.g., Sarkar (1981, p. 560, Theorem 3.1).

Keywords and phrases

covariance matrix maximum likelihood estimation regression coefficient 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Govindarajalu, Z. (1975). Best linear unbiased and invariant estimators for regression parameters based on ordered observations, inApplied Statistics (Ed. R. P. Gupta) North-Holland, New York.Google Scholar
  2. Lefland, P.S.H. and Praag, B.M.S. Van (1971). A procedure to estimate relative powers in binary contact and an application to Dutch football league results.Statistica Neerlandica,25, 63–84.CrossRefGoogle Scholar
  3. Revankar, N. S. (1974). Some finite sample results in the context of two seemingly unrelated regression equations.J. Amer. Statist. Asso.,69, 187–90.zbMATHCrossRefMathSciNetGoogle Scholar
  4. Sarkar, S. K. (1981). Some multivariate linear regression testing problems with additional observations.J. Multi. Anal.,11, 556–567.zbMATHCrossRefGoogle Scholar
  5. Zellner, Arnold (1962). An efficient method of estimating seemingley unrelated regressions and tests of aggregation bias.J. of Amer. Statist. Assoc.,57, 348–368.zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag 1998

Authors and Affiliations

  • A. K. Gupta
    • 1
  • D. G. Kabe
    • 2
  1. 1.Department of Mathematics and StatisticsBowling Green State UniversityBowling GreenUSA
  2. 2.Department of Mathematics and Computer ScienceSt. Mary’s UniversityNova ScotiaCanada

Personalised recommendations