Distribution of the Estimator for Peak of a Regression Function Using the Concomitants of Extreme Oder Statistics

  • Kim, S.H (Department of Statistics and Information, Anyang University) ;
  • Kim, T.S. (Department of Statistics, Won-Kwang University)
  • Published : 1998.12.01

Abstract

For a random sample of size n from general linear model, $Y_i= heta(X_i)+varepsilon_i,;let Y_{in}$ denote the ith oder statistics of the Y sample values. The X-value associated with $Y_{in}$ is denoted by $X_{[in]}$ and is called the concomitant of ith order statistics. The estimator of the location of a maximum of a regression function, $ heta$($\chi$), was proposed by (equation omitted) and was found the convergence rate of it under certain weak assumptions on $ heta$. We will discuss the asymptotic distributions of both $ heta(X_{〔n-r+1〕}$) and (equation omitted) when r is fixed as nolongrightarrow$\infty$(i.e. extreme case) on the basis of the theorem of the concomitants of order statistics. And the will investigate the asymptotic behavior of Max{$\theta$( $X_{〔n-r+1:n〕/}$ ), . , $\theta$( $X_{〔n:n〕}$)}as an estimator for the peak of a regression function.

Keywords

References

  1. Annals of Statistics v.2 Convergence of sample paths of normalized sums of induced order statistics Bhattacharya, P. K.
  2. Iduced order statistics: Theory and Applications, Handbook of Statistics Bhattacharya, P. K.;P. R. Krishnaiah(ed.);P. K. Sen(ed.)
  3. Journal of Royal Statistical Society Series B v.13 On the experimental attainment of optimum condition Box, G. E. P.;Wilson, K. B.
  4. Proceedings of the 1990 Taipei Symposium in Statistics Optimization of blast furnace burden distribution Changchien, G. M.;M. T. Chao(Ed.);P. E. Cheng(Ed.)
  5. Annals of Statistics v.3 Lower rate of convergence for locating a maximum of a function Chen, H.
  6. Journal of Multivariate Analysis v.57 Estimation of the location of the maximum of a regression function using extreme order statistics Chen, H.;Huang, M. L.;Huang, W. J.
  7. Bulletin of International Institute v.4 Concomitants of order statistics David, H. A.
  8. Journal Applied Probability v.11 The asymptotic theory of concomitants of order statistics David, H. A.;Galambos, J.
  9. Annals of Statistics v.5 Distribution and expected value of the ranks of a concomitant of an order statistics David, H. A.;O'Connell, M. J.;Yang, S. S.
  10. IEEE Transaction Information Theory v.IT-24 The uniform convergence of nearest neighbor regression function estimators and their application in optimization Devroye, L. P.
  11. Annals of Mathematical Statistics v.38 Stochastic approximation of minima with improved asymptotic speed Fabian, V.
  12. Annals of Mathematics v.44 Sur la distribution limite due terme maximum d'une serie aleatoire Gnedenko, B.
  13. Journal of American Statistical Association v.76 Estimation of the minimum of a function using order statistics Haan, L. DE
  14. Annals of Mathematical Statistics v.12 Experimental determination of the maximum of a function Hotelling H.
  15. Annals of Mathematical Statistics v.23 Stochastic estimation of the maximum of a regression function Kieffer, J.;Wolfowitz, J.
  16. Annals of Statistics v.17 Adaptive nonparametric peak estimation Muller, H. G.
  17. Theory of Probability Applied v.9 On estimating regression Nadaraya, E. A.
  18. Annals of Statistics v.22 Distribution of the maximum of concomitants of selected order statistics Nagaraja, H. N.;David, H. A.
  19. Approximate Distributions of Order Sttistics: With Applications to Nonparametric Statistics Reiss, R. D.
  20. Rev. Math. Union Interbalkanique v.1;2 La distribution de la plus grande den valeurs. Reproduced in Selected Papers of Richard von Mises von Mises, R.
  21. Annals of Statistics General distribution theory of the concomitants of order statistics Yang, S. S.