Non-parametric estimation of the residual distribution

Michael G. Akritas; Ingrid Van Keilegom

doi:10.1111/1467-9469.00254

Non-parametric estimation of the residual distribution

Michael G. Akritas, Ingrid Van Keilegom

Statistics

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

143 Scopus citations

Abstract

Consider a heteroscedastic regression model Y = m(X) + σ(X)ε, where the functions m and σ are "smooth", and ε is independent of X. An estimator of the distribution of ε based on non-parametric regression residuals is proposed and its weak convergence is obtained. Applications to prediction intervals and goodness-of-fit tests are discussed.

Original language	English (US)
Pages (from-to)	549-567
Number of pages	19
Journal	Scandinavian Journal of Statistics
Volume	28
Issue number	3
DOIs	https://doi.org/10.1111/1467-9469.00254
State	Published - Sep 2001

All Science Journal Classification (ASJC) codes

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1111/1467-9469.00254

Cite this

@article{f5e4283af3144ec59a1916b3d2bb704d,

title = "Non-parametric estimation of the residual distribution",

abstract = "Consider a heteroscedastic regression model Y = m(X) + σ(X)ε, where the functions m and σ are {"}smooth{"}, and ε is independent of X. An estimator of the distribution of ε based on non-parametric regression residuals is proposed and its weak convergence is obtained. Applications to prediction intervals and goodness-of-fit tests are discussed.",

author = "Akritas, {Michael G.} and {Van Keilegom}, Ingrid",

year = "2001",

month = sep,

doi = "10.1111/1467-9469.00254",

language = "English (US)",

volume = "28",

pages = "549--567",

journal = "Scandinavian Journal of Statistics",

issn = "0303-6898",

publisher = "Wiley-Blackwell Publishing Ltd",

number = "3",

}

TY - JOUR

T1 - Non-parametric estimation of the residual distribution

AU - Akritas, Michael G.

AU - Van Keilegom, Ingrid

PY - 2001/9

Y1 - 2001/9

N2 - Consider a heteroscedastic regression model Y = m(X) + σ(X)ε, where the functions m and σ are "smooth", and ε is independent of X. An estimator of the distribution of ε based on non-parametric regression residuals is proposed and its weak convergence is obtained. Applications to prediction intervals and goodness-of-fit tests are discussed.

AB - Consider a heteroscedastic regression model Y = m(X) + σ(X)ε, where the functions m and σ are "smooth", and ε is independent of X. An estimator of the distribution of ε based on non-parametric regression residuals is proposed and its weak convergence is obtained. Applications to prediction intervals and goodness-of-fit tests are discussed.

UR - http://www.scopus.com/inward/record.url?scp=0035457247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035457247&partnerID=8YFLogxK

U2 - 10.1111/1467-9469.00254

DO - 10.1111/1467-9469.00254

M3 - Article

AN - SCOPUS:0035457247

SN - 0303-6898

VL - 28

SP - 549

EP - 567

JO - Scandinavian Journal of Statistics

JF - Scandinavian Journal of Statistics

IS - 3

ER -

Non-parametric estimation of the residual distribution

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this