A Note on Disturbance Variance Estimator in Panel Data with Equicorrelated Error Components

  • Seuck Heun Song (Dept. of Statistics, Duksung Women's University, Seoul, 132-174, KOREA)
  • Published : 1995.12.01

Abstract

The ordinary least square estimator of the disturbance variance in the pooled cross-sectional and time series regression model is shown to be asymptotically unbiased without any restrictions on the regressor matrix when the disturbances follow an equicorrelated error component models.

Keywords

References

  1. International Economic Review v.12 The estimation of variances on a variance components model Amemiya,T.
  2. Empirical Economics v.17 A survey of recent theoretical developments in the econometrics of panel data Baltagi,B.;Raj,B.
  3. Statistical Papers v.34 Useful matrix transformations for panel data analysis: a survey Baltagi,B.
  4. Statistical Papers v.34 Consistency, asymptotic unbiasedness and bounds on the bias of s² in the linear regression model with error component disturbances Baltagi,B.;Kroemer,W.
  5. The American Statistician v.40 Bias of s² in linear regression with errors Dufour,J.M.
  6. Journal of Econometrics v.37 Estimations of the disturbance variance in econometric models Dufour,J.M.
  7. Matrices with Applications in Statistics)2nd ed.0 Graybill,F.A.
  8. Matrix Algebre Horn,R.A.;Johnson,C.R.
  9. Topics in Matrix Analysis Horn,R.A.;Johnson,C.R.
  10. Analysis of Panel Data Hsiao,C.
  11. The Review of Economics and Statistics v.74 Bias of s² in the linear regression model with correlated errors Kiviet,J.F.;Kraemer,W.
  12. Statistical Papers v.32 The asymptotic unbiasedness of s² in the linear regression model with AR(1)-disturbances Kraemer,W.
  13. Journal of Econometrics v.32 Random group effects and the precision of regression estimates Moulton,B.R.
  14. Econometrica v.47 A note on error components model Nerlove,M.
  15. Econometrica v.45 Bounds for the bias of the least squares estimator of s² in case of a first-order autoregressive process(positive autocorrelation) Neudecker,H.
  16. Econometrica v.46 Bounds for the bias of LS stimator in case of a first-order (positive) autoregressive process where regression contains a constant term Neudecker,H.
  17. Technical Report NR. 3 Consistency and asymptotic unbiasedness of s² in the linear regression model with serially correlated two-way error components Song,S.H.
  18. Consistency and asymptotic unbiasedness of s² in the linear regression model with serially correlated error components(submitted for publication) Song,S.H.
  19. Econometrica v.40 The exact finite sample properties of the estimators of coefficients in the error components regression models Swamy,P.A.;Arora,S.S.
  20. Econometrica v.42 Bounds on th variace of regression coefficients due to heteroscedastic or autoregressive errors Sathe,S.T.;Vinod,H.D.
  21. Econometrica v.37 The use of error components models in combining cross-section with time-series data Wallace,T.D.;Hussain,A.
  22. Biometrika v.42 Serial correlation in regression analysis I Watson,G.S.