Non linear parametric mode regression

Salah Khardani; Anne Françoise Yao

doi:10.1080/03610926.2014.1002940

Non linear parametric mode regression

Salah Khardani, Anne Françoise Yao

Clermont-Auvergne University

Research output: Contribution to journal › Article › peer-review

Abstract

In this article, we propose a semi-parametric mode regression for a non linear model. We use an expectation-maximization algorithm in order to estimate the regression coefficients of modal non linear regression. We also establish asymptotic properties for the proposed estimator under assumptions of the error density. We investigate the performance through a simulation study.

Original language	English
Pages (from-to)	3006-3024
Number of pages	19
Journal	Communications in Statistics - Theory and Methods
Volume	46
Issue number	6
DOIs	https://doi.org/10.1080/03610926.2014.1002940
Publication status	Published - 19 Mar 2017
Externally published	Yes

Keywords

Asymptotic normality
Kernel smoothing
Mode estimation
Non linear model
Parametric regression

Access to Document

10.1080/03610926.2014.1002940

Cite this

@article{509354f4badc43619c4e1897bd6f2739,

title = "Non linear parametric mode regression",

abstract = "In this article, we propose a semi-parametric mode regression for a non linear model. We use an expectation-maximization algorithm in order to estimate the regression coefficients of modal non linear regression. We also establish asymptotic properties for the proposed estimator under assumptions of the error density. We investigate the performance through a simulation study.",

keywords = "Asymptotic normality, Kernel smoothing, Mode estimation, Non linear model, Parametric regression",

author = "Salah Khardani and Yao, \{Anne Fran{\c c}oise\}",

note = "Publisher Copyright: {\textcopyright} 2017 Taylor \& Francis Group, LLC.",

year = "2017",

month = mar,

day = "19",

doi = "10.1080/03610926.2014.1002940",

language = "English",

volume = "46",

pages = "3006--3024",

journal = "Communications in Statistics - Theory and Methods",

issn = "0361-0926",

number = "6",

}

TY - JOUR

T1 - Non linear parametric mode regression

AU - Khardani, Salah

AU - Yao, Anne Françoise

PY - 2017/3/19

Y1 - 2017/3/19

N2 - In this article, we propose a semi-parametric mode regression for a non linear model. We use an expectation-maximization algorithm in order to estimate the regression coefficients of modal non linear regression. We also establish asymptotic properties for the proposed estimator under assumptions of the error density. We investigate the performance through a simulation study.

AB - In this article, we propose a semi-parametric mode regression for a non linear model. We use an expectation-maximization algorithm in order to estimate the regression coefficients of modal non linear regression. We also establish asymptotic properties for the proposed estimator under assumptions of the error density. We investigate the performance through a simulation study.

KW - Asymptotic normality

KW - Kernel smoothing

KW - Mode estimation

KW - Non linear model

KW - Parametric regression

U2 - 10.1080/03610926.2014.1002940

DO - 10.1080/03610926.2014.1002940

M3 - Article

AN - SCOPUS:85002194601

SN - 0361-0926

VL - 46

SP - 3006

EP - 3024

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

IS - 6

ER -

Non linear parametric mode regression

Abstract

Keywords

Access to Document

Fingerprint

Cite this