Nonparametric regression penalizing deviations from additivity

被引:3
|
作者
Studer, M [1 ]
Seifert, B [1 ]
Gasser, T [1 ]
机构
[1] Univ Zurich, Dept Biostat, ISPM, CH-8006 Zurich, Switzerland
来源
ANNALS OF STATISTICS | 2005年 / 33卷 / 03期
关键词
nonparametric estimation; additive models; model choice; curse of dimensionality; regularization; parameter selection; AIC;
D O I
10.1214/009053604000001246
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
Due to the curse of dimensionality, estimation in a multidimensional nonparametric regression model is in general not feasible. Hence, additional restrictions are introduced, and the additive model takes a prominent place. The restrictions imposed can lead to serious bias. Here, a new estimator is proposed which allows penalizing the nonadditive part of a regression function. This offers a smooth choice between the full and the additive model. As a byproduct, this penalty leads to a regularization in sparse regions. If the additive model does not hold, a small penalty introduces an additional bias compared to the full model which is compensated by the reduced bias due to using smaller bandwidths. For increasing penalties, this estimator converges to the additive smooth backfitting estimator of Mammen, Linton and Nielsen [Ann. Statist. 27 (1999) 1443-1490]. The structure of the estimator is investigated and two algorithms are provided. A proposal for selection of tuning parameters is made and the respective properties are studied. Finally, a finite sample evaluation is performed for simulated and ozone data.
引用
收藏
页码:1295 / 1329
页数:35
相关论文
共 50 条
  • [1] A test for additivity in nonparametric regression
    Derbort, S
    Dette, H
    Munk, A
    [J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2002, 54 (01) : 60 - 82
  • [2] Testing for additivity in nonparametric regression
    Eubank, RL
    Hart, JD
    Simpson, DG
    Stefanski, LA
    [J]. ANNALS OF STATISTICS, 1995, 23 (06): : 1896 - 1920
  • [3] A Test for Additivity in Nonparametric Regression
    Stephan Derbort
    Holger Dette
    Axel Munk
    [J]. Annals of the Institute of Statistical Mathematics, 2002, 54 : 60 - 82
  • [4] Testing for additivity in nonparametric quantile regression
    Dette, Holger
    Guhlich, Matthias
    Neumeyer, Natalie
    [J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2015, 67 (03) : 437 - 477
  • [5] Testing for additivity in nonparametric quantile regression
    Holger Dette
    Matthias Guhlich
    Natalie Neumeyer
    [J]. Annals of the Institute of Statistical Mathematics, 2015, 67 : 437 - 477
  • [6] Testing for additivity in nonparametric heteroscedastic regression models
    Zambom, Adriano Zanin
    Kim, Jongwook
    [J]. JOURNAL OF NONPARAMETRIC STATISTICS, 2020, 32 (03) : 793 - 813
  • [7] Optimal testing for additivity in multiple nonparametric regression
    Abramovich, Felix
    De Feis, Italia
    Sapatinas, Theofanis
    [J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2009, 61 (03) : 691 - 714
  • [8] Optimal testing for additivity in multiple nonparametric regression
    Felix Abramovich
    Italia De Feis
    Theofanis Sapatinas
    [J]. Annals of the Institute of Statistical Mathematics, 2009, 61 : 691 - 714
  • [9] Testing additivity in nonparametric regression under random censorship
    Debbarh, Mohammed
    Viallon, Vivian
    [J]. STATISTICS & PROBABILITY LETTERS, 2008, 78 (16) : 2584 - 2591
  • [10] Testing additivity in nonparametric regression under mixing conditions
    Camlong-Viot, C
    [J]. COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE I-MATHEMATIQUE, 2001, 333 (09): : 877 - 880