Point separation in logistic regression on Hilbert space-valued variables

被引：4

作者：

Kazakeviciute, Agne ^{[1
]}

Olivo, Malini ^{[2
,3
]}

机构：

[1] UCL, Dept Stat Sci, London, England

[2] ASTAR, Singapore, Singapore

[3] Natl Univ Ireland, Sch Phys, Galway, Ireland

来源：

STATISTICS & PROBABILITY LETTERS | 2017年 / 128卷

关键词：

Point separation; Functional data analysis; Logistic regression; MODELS;

D O I：

10.1016/j.spl.2017.04.019

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：

We study point separation for the logistic regression model for Hilbert space-valued variables. We prove that the separating hyperplane can be found from a finite set of candidates and give an upper bound for the probability of point separation. (C) 2017 Elsevier B.V. All rights reserved.

引用

收藏

页码：84 / 88

页数：5

相关论文

共 18 条

[1] Discussion of different logistic models with functional data. Application to Systemic Lupus Erythematosus [J].

Aguilera, Ana M. ;

Escabias, Manuel ;

Valderrama, Mariano J. .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 53 (01) :151-163

[2]

ALBERT A, 1984, BIOMETRIKA, V71, P1

[3] Penalized spline approaches for functional logit regression [J].

Carmen Aguilera-Morillo, M. ;

Aguilera, Ana M. ;

Escabias, Manuel ;

Valderrama, Mariano J. .

TEST, 2013, 22 (02) :251-277

[4] Measuring overlap in binary regression [J].

Christmann, A ;

Rousseeuw, PJ .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2001, 37 (01) :65-75

[5] Robust Principal Component Functional Logistic Regression [J].

Denhere, Melody ;

Billor, Nedret .

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2016, 45 (01) :264-281

[6] Functional PLS logit regression model [J].

Escabias, M. ;

Aguilera, A. M. ;

Valderrama, M. J. .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2007, 51 (10) :4891-4902

[7] Principal component estimation of functional logistic regression: Discussion of two different approaches [J].

Escabias, M ;

Aguilera, AM ;

Valderrama, MJ .

JOURNAL OF NONPARAMETRIC STATISTICS, 2004, 16 (3-4) :365-384

[8] BIAS REDUCTION OF MAXIMUM-LIKELIHOOD-ESTIMATES [J].

FIRTH, D .

BIOMETRIKA, 1993, 80 (01) :27-38

[9] Simpson's paradox - aggregating and partitioning populations in health disparities of lung cancer patients [J].

Fu, P. ;

Panneerselvam, A. ;

Clifford, B. ;

Dowlati, A. ;

Ma, P. C. ;

Zeng, G. ;

Halmos, B. ;

Leidner, R. S. .

STATISTICAL METHODS IN MEDICAL RESEARCH, 2015, 24 (06) :937-948

[10] Asymptotic properties of a double penalized maximum likelihood estimator in logistic regression [J].

Gao, Sujuan ;

Shen, Jianzhao .

STATISTICS & PROBABILITY LETTERS, 2007, 77 (09) :925-930