Local polynomial regression with an ordinal covariate

Zonglin He, Jean D. Opsomer

Research output: Contribution to journalArticle

Abstract

We are interested in fitting a nonparametric regression model to data when the covariate is an ordered categorical variable. We extend the local polynomial estimator, which normally requires continuous covariates, to a local polynomial estimator that allows for ordered categorical covariates. We derive the asymptotic conditional bias and variance under the assumption that the categories correspond to quantiles of an unobserved continuous latent variable. We conduct a simulation study with two patterns of ordinal data to evaluate our estimator.

Original languageEnglish (US)
Pages (from-to)516-531
Number of pages16
JournalJournal of Nonparametric Statistics
Volume27
Issue number4
DOIs
StatePublished - Oct 2 2015

Fingerprint

Local Polynomial Regression
Covariates
Local Polynomial
Estimator
Ordinal Data
Categorical variable
Nonparametric Model
Continuous Variables
Latent Variables
Nonparametric Regression
Quantile
Categorical
Regression Model
Simulation Study
Evaluate
Local polynomial
Polynomial regression

Keywords

  • categorical covariate
  • kernel regression

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Local polynomial regression with an ordinal covariate. / He, Zonglin; Opsomer, Jean D.

In: Journal of Nonparametric Statistics, Vol. 27, No. 4, 02.10.2015, p. 516-531.

Research output: Contribution to journalArticle

He, Zonglin ; Opsomer, Jean D. / Local polynomial regression with an ordinal covariate. In: Journal of Nonparametric Statistics. 2015 ; Vol. 27, No. 4. pp. 516-531.
@article{b84c8c95d893479faece3f5353617007,
title = "Local polynomial regression with an ordinal covariate",
abstract = "We are interested in fitting a nonparametric regression model to data when the covariate is an ordered categorical variable. We extend the local polynomial estimator, which normally requires continuous covariates, to a local polynomial estimator that allows for ordered categorical covariates. We derive the asymptotic conditional bias and variance under the assumption that the categories correspond to quantiles of an unobserved continuous latent variable. We conduct a simulation study with two patterns of ordinal data to evaluate our estimator.",
keywords = "categorical covariate, kernel regression",
author = "Zonglin He and Opsomer, {Jean D.}",
year = "2015",
month = "10",
day = "2",
doi = "10.1080/10485252.2015.1078462",
language = "English (US)",
volume = "27",
pages = "516--531",
journal = "Journal of Nonparametric Statistics",
issn = "1048-5252",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

TY - JOUR

T1 - Local polynomial regression with an ordinal covariate

AU - He, Zonglin

AU - Opsomer, Jean D.

PY - 2015/10/2

Y1 - 2015/10/2

N2 - We are interested in fitting a nonparametric regression model to data when the covariate is an ordered categorical variable. We extend the local polynomial estimator, which normally requires continuous covariates, to a local polynomial estimator that allows for ordered categorical covariates. We derive the asymptotic conditional bias and variance under the assumption that the categories correspond to quantiles of an unobserved continuous latent variable. We conduct a simulation study with two patterns of ordinal data to evaluate our estimator.

AB - We are interested in fitting a nonparametric regression model to data when the covariate is an ordered categorical variable. We extend the local polynomial estimator, which normally requires continuous covariates, to a local polynomial estimator that allows for ordered categorical covariates. We derive the asymptotic conditional bias and variance under the assumption that the categories correspond to quantiles of an unobserved continuous latent variable. We conduct a simulation study with two patterns of ordinal data to evaluate our estimator.

KW - categorical covariate

KW - kernel regression

UR - http://www.scopus.com/inward/record.url?scp=84943449755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943449755&partnerID=8YFLogxK

U2 - 10.1080/10485252.2015.1078462

DO - 10.1080/10485252.2015.1078462

M3 - Article

AN - SCOPUS:84943449755

VL - 27

SP - 516

EP - 531

JO - Journal of Nonparametric Statistics

JF - Journal of Nonparametric Statistics

SN - 1048-5252

IS - 4

ER -