Finite-Sample, Small-Dispersion Asymptotic Optimality of the Non-Linear Least Squares Estimator

  • So, Beong-Soo (Department of Statistics, Ewha Womens University, Seoul 120-750)
  • 발행 : 1995.12.01

초록

We consider the following type of general semi-parametric non-linear regression model : $y_i = f_i(\theta) + \epsilon_i, i=1, \cdots, n$ where ${f_i(\cdot)}$ represents the set of non-linear functions of the unknown parameter vector $\theta' = (\theta_1, \cdots, \theta_p)$ and ${\epsilon_i}$ represents the set of measurement errors with unknown distribution. Under suitable finite-sample, small-dispersion asymptotic framework, we derive a general lower bound for the asymptotic mean squared error (AMSE) matrix of the Gauss-consistent estimator of $\theta$. We then prove the fundamental result that the general non-linear least squares estimator (NLSE) is an optimal estimator within the class of all regular Gauss-consistent estimators irrespective of the type of the distribution of the measurement errors.

키워드

참고문헌

  1. Annals of Statistics v.11 On BAN Estimator for Chi-Squared Criteria Bemis,K.G.;Bhapkar,V.P.
  2. Annals of Methematical Statistics v.29 A Method of Generating BAN Estimates with Application to the Estimation of Bacterial Densities Ferguson,T.S.
  3. Annals of Mathematical Statistics v.36 Non-Linear Least Squares Estimation Hartley,H.O.;Booker,A.
  4. Annals of Mathematical Statistics v.40 Asymptotic Properties of Non-Linear Least Squares Estimators Jennrich,R.I.
  5. Journal of the Royal Statistical Society v.B 49 Exponential Dispersion Models Jorgensen,B.
  6. Annals of Statistics v.11 Quasi-Likelihood Functions McCullagh,P.
  7. Generalized Linear Models(2nd ed.) Nelder,J.A.;McCullagh,P.
  8. Proceedings of the Berkeley Symposium on Mathematical Statistics and Probability v.1 Contribution to the Theory of the χ² Test Neyman,J.
  9. Journal of the Korean Society for Quality Management v.22-2 A Note on the Small Sample Calibration So,B.S.
  10. Encyclopedia of Statistics v.3 Sprott,D.A.
  11. Annals of Statistics v.40 On the Least Squares Estimation of Non-Linear Relations Villegas,C.
  12. Biometrika v.61 Quasi-Likelihood Functions, Generalized Linear Models, and the Gauss-Newton Method Wedderburn,R.W.M.
  13. Annals of Statistics v.9 Asymptotic Theory of the Non-Linear Least Squares Estimation Wu,C.F.