Pitfalls in the Application of the COTE in a Linear Regression Model with Seasonal Data

  • Seuck Heun Song (Department of Statistics, Duksung Women's University, Seoul 132-174, Korea) ;
  • YouSung Park (Department of Statistics, Korea University, Seoul, 136-701, Korea)
  • Published : 1997.08.01

Abstract

When the disturbances in the linear repression medel are generated by a seasonal autoregressive scheme the Cochrane Orcutt transformation estimator (COTE) is a well known alternative to Generalized Least Squares estimator (GLSE). In this paper it is analyzed in which situation the Ordinary Least Squares estimator (OLSE) is always better than COTE for positive autocorrelation in terms of efficiency which is here defined as the ratio of the total variances.

Keywords

References

  1. Applied Statistics v.37 Leverage and influence in autocorrelated regressionmodels Puterman, M.L.
  2. International Economic Review v.20 On the retention of first observation inserial correlation adjustment of regression models Maeshiro, A.
  3. Econometrica v.36 A transformation used to circumvent the problem of autocorrelation Kadiyala, K.R.
  4. Review of Economics and Statistics v.58 Autoregressive transformation, trended independent variables and autocorrelated disturbance term Maeshiro, A.
  5. Journal of American Statistical Association v.62 Finite sample efficiency of ordinary least squares in the linear regression model with autocorrelated errors Kraemer, W.
  6. Applied Statistics v.27 The effect of the first observation in regression models with first-order autoregressive disturbance Poirier, D.J.
  7. Advanced Econometrics Methods Fomby, J.B.;Hill, R.C.;Johnson, S.R.
  8. Australian Journal of Statistics v.31 The efficiency of the cochrane-orcutt procedure Hoque, A.
  9. Journal of Econometrics v.16 Omission of an observation from a regression analysis Doran, H.E.
  10. The Theory and Practice of Econometrices Judge, G.G.;Griffiths, W.E.;Hill, R.C.;Luekepohl, H.;Lee, T.C.
  11. Econometrica v.50 Note on estimating linear trend when residuals are autocorrelated Kraemer, W.
  12. Communications on Statistics-Theory and Method v.22 Leverage and Cochrane Orcutt estimation in the linear regression Stemann, D.;Trenkler, G.
  13. Journal of Econometrics v.13 Estimating the autocorre;ated error model with trended data Park, R.E.;Mitchell, B.M.
  14. Review of Economics amd Statistics v.62 Autocorrelation and trended explanatory variables:a rely Maeshiro, A.
  15. Statistical Theory and Data Analysis Ⅱ Efficiency of least squares in a linear model with autocorrelated disturbances Iwasaki, M.;K. Matusita(Hrsg.)