作成者 |
|
|
|
本文言語 |
|
出版者 |
|
|
発行日 |
|
収録物名 |
|
巻 |
|
号 |
|
開始ページ |
|
終了ページ |
|
出版タイプ |
|
アクセス権 |
|
Crossref DOI |
|
関連DOI |
|
|
関連URI |
|
|
関連情報 |
|
|
概要 |
Let $ {(X_i, Y_i) : i = 1, 2, ldots } $ be a sequence of stationary independent random vectors in $ Re^{(2)} $ with a continuous distribution, and let $ G_x(cdot) $ denote the conditional distribution... function of $ Y_1 $ given $ X_1 = x $. In this paper, Bahadur's almost sure representation for the sample conditional quantile $ hat{G}_{nx}^{-1} $, $ 0 < lambda <1 $, is established, where $ hat{G}_{nx} $, is a smoothed (rank nearest neighbor or the Nadaraya-Watson type) estimator of $ hat{G}_{nx} $. Such representations arc useful in the study of asymptotics of functionals of conditional quantiles.続きを見る
|