Elsevier

Journal of Econometrics

Volume 23, Issue 2, October 1983, Pages 165-191
Journal of Econometrics

On the relative efficiency of estimators which include the initial observations in the estimation of seemingly unrelated regressions with first-order autoregressive disturbances

https://doi.org/10.1016/0304-4076(93)90075-GGet rights and content

Abstract

The generalized least squares estimator for a seemingly unrelated regressions model with first-order vector autoregressive disturbances is outlined, and its efficiency is compared with that of an approximate generalized least squares estimator which ignores the first observation. A scalar index for the loss of efficiency is developed and applied to a special case where the matrix of autoregressive parameters is diagonal and the regressors are smooth. Also, for a more general model, a Monte Carlo study is used to investigate the relative efficiencies of various estimators. The results suggest that Maeshiro (1980) has overstated the case for the exact generalized least squares estimator, because, in many circumstances, it is only marginally better than the approximate generalized least squares estimator.

References (20)

  • T.S. Breusch

    Useful invariance results for generalized regression models

    Journal of Econometrics

    (1980)
  • H.E. Doran

    Omission of an observation from a regression analysis: A discussion on efficiency loss, with applications

    Journal of Econometrics

    (1981)
  • C.M. Beach et al.

    A maximum likelihood procedure for regression with autocorrelated errors

    Econometrica

    (1978)
  • C.M. Beach et al.

    Maximum likelihood estimation of singular equation systems with autoregressive disturbances

    International Economic Review

    (1979)
  • J.S. Chipman

    Efficiency of least squares estimation of linear trend when residuals are autocorrelated

    Econometrica

    (1979)
  • P.J. Dhrymes

    Introductory econometrics

    (1978)
  • F.A. Graybill

    Introduction to matrices with applications in statistics

    (1969)
  • D.K. Guilkey et al.

    Estimation of seemingly unrelated regressions with vector autoregressive errors

    Journal of the American Statistical Association

    (1973)
  • G.G. Judge et al.

    Introduction to the theory and practice of econometrics

    (1982)
  • K.R. Kadiyala

    A transformation used to circumvent the problem of autocorrelation

    Econometrica

    (1968)
There are more references available in the full text version of this article.

Cited by (17)

  • Differential impact of Korean banking system reforms on bank productivity

    2010, Journal of Banking and Finance
    Citation Excerpt :

    We address this problem by using a variant of the Prais and Winsten (1954) estimator proposed by Park and Mitchell (1980) to make first-order autocorrelation adjustments to the variables. This estimator is consistent and performs especially well for short time series and trended data in relation to several other estimates (Doran and Griffiths, 1983). It also reduces the extent to which the serial correlation coefficient tends to be underestimated by simpler methods (Kmenta and Gilbert, 1970).

  • Competition, fee-for-service requirements, and government performance: Evidence on the Federal Reserve

    2002, Journal of Accounting and Public Policy
    Citation Excerpt :

    As in Banker et al. (1996), I control for autocorrelation by using a variant of the Prais–Winsten (1954) estimator proposed by Park and Mitchell (1980) to make first-order autocorrelation adjustments to the variables. This estimator is consistent and performs especially well for short time series and trended data relative to several other estimators (Doran and Griffiths, 1983). It also reduces the extent to which the autocorrelation coefficient tends to be underestimated (Kmenta and Gilbert, 1970).

View all citing articles on Scopus

A substantial part of this work was done while Doran was a Fellow of the Alexander von Humboldt Foundation at the University of Bonn. Also, we are grateful to an anonymous referee for some valuable suggestions.

View full text