Non-crossing non-parametric estimates of quantile curves

被引:92
|
作者
Dette, Holger [1 ]
Volgushev, Stanislav [1 ]
机构
[1] Ruhr Univ Bochum, Fak Math, D-44780 Bochum, Germany
关键词
conditional distribution; crossing quantile curves; local linear estimate; Nadaraya; Watson estimate; quantile estimation;
D O I
10.1111/j.1467-9868.2008.00651.x
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Since the introduction by Koenker and Bassett, quantile regression has become increasingly important in many applications. However, many non-parametric conditional quantile estimates yield crossing quantile curves (calculated for various p is an element of (0, 1)). We propose a new non-parametric estimate of conditional quantiles that avoids this problem. The method uses an initial estimate of the conditional distribution function in the first step and solves the problem of inversion and monotonization with respect to p is an element of (0, 1) simultaneously. It is demonstrated that the new estimates are asymptotically normally distributed with the same asymptotic bias and variance as quantile estimates that are obtained by inversion of a locally constant or locally linear smoothed conditional distribution function. The performance of the new procedure is illustrated by means of a simulation study and some comparisons with the currently available procedures which are similar in spirit with the method proposed are presented.
引用
收藏
页码:609 / 627
页数:19
相关论文
共 50 条
  • [1] ESTIMATION OF NON-CROSSING QUANTILE REGRESSION CURVES
    Cai, Yuzhi
    Jiang, Tao
    [J]. AUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS, 2015, 57 (01) : 139 - 162
  • [2] Parametric estimation of non-crossing quantile functions
    Sottile, Gianluca
    Frumento, Paolo
    [J]. STATISTICAL MODELLING, 2023, 23 (02) : 173 - 195
  • [3] Quantile regression in varying-coefficient models: non-crossing quantile curves and heteroscedasticity
    Andriyana, Y.
    Gijbels, I.
    Verhasselt, A.
    [J]. STATISTICAL PAPERS, 2018, 59 (04) : 1589 - 1621
  • [4] Non-crossing quantile regressions by SVM
    Takeuchi, I
    Furuhashi, T
    [J]. 2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 401 - 406
  • [5] Quantile regression in varying-coefficient models: non-crossing quantile curves and heteroscedasticity
    Y. Andriyana
    I. Gijbels
    A. Verhasselt
    [J]. Statistical Papers, 2018, 59 : 1589 - 1621
  • [6] ` Reference curves based on non-parametric quantile regression
    Gannoun, A
    Girard, S
    Guinot, C
    Saracco, J
    [J]. STATISTICS IN MEDICINE, 2002, 21 (20) : 3119 - 3135
  • [7] Non-crossing convex quantile regression
    Dai, Sheng
    Kuosmanen, Timo
    Zhou, Xun
    [J]. ECONOMICS LETTERS, 2023, 233
  • [8] ON NON-PARAMETRIC ESTIMATES OF DENSITY FUNCTIONS AND REGRESSION CURVES
    NADARAYA, EA
    [J]. THEORY OF PROBILITY AND ITS APPLICATIONS,USSR, 1965, 10 (01): : 186 - &
  • [9] Non-crossing frameworks with non-crossing reciprocals
    Orden, D
    Rote, G
    Santos, F
    Servatius, B
    Servatius, H
    Whiteley, W
    [J]. DISCRETE & COMPUTATIONAL GEOMETRY, 2004, 32 (04) : 567 - 600
  • [10] Non-Crossing Frameworks with Non-Crossing Reciprocals
    David Orden
    Günter Rote
    Francisco Santos
    Brigitte Servatius
    Herman Servatius
    Walter Whiteley
    [J]. Discrete & Computational Geometry, 2004, 32 : 567 - 600