Some remarks about the gasser-sroka-jennen-steinnietz variance estimator

Naomi S. Altman, C. P. Paulson

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This article proposes some simplifications of the residual variance estimator of Gasser, Sroka, and jennen-Steinmetz (GSJ, 1986) which is often used in conjunction with nonparametric regression. The GSJ estimator is a quadratic form of the data, which depends on the relative spacings of the design points. When the errors are independent, identically distributed Gaussian variables, and the true regression curve is flat, theestimate is distributed as a weighted sum of x2 variables. By matching the first two moments, the distribution can be approximated by a x2with degrees of freedom determined by the coefficients of the quadratic for. Computation ofthe estimated degrees of freedom requires computing the trace of the square of an n x n matrix, where n is the number of design points. In this article, (n-2)/3 is shown to be a conservative estimate of the approximate degrees of freedom, and (n-2)/2 is shown to be conservative for many designs. In addition, a simplified version of the estimator is shown to be asymptotically equivalent, under many conditions.

Original languageEnglish (US)
Pages (from-to)1045-1051
Number of pages7
JournalCommunications in Statistics - Theory and Methods
Volume22
Issue number4
DOIs
StatePublished - Jan 1 1993

Fingerprint

Variance Estimator
Degree of freedom
Estimator
Asymptotically equivalent
Nonparametric Regression
Weighted Sums
Quadratic form
Identically distributed
Simplification
Spacing
Regression
Trace
Moment
Curve
Computing
Coefficient
Estimate
Design

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

Altman, Naomi S. ; Paulson, C. P. / Some remarks about the gasser-sroka-jennen-steinnietz variance estimator. In: Communications in Statistics - Theory and Methods. 1993 ; Vol. 22, No. 4. pp. 1045-1051.
@article{c83331e0272b483a89f7fe52ac21b979,
title = "Some remarks about the gasser-sroka-jennen-steinnietz variance estimator",
abstract = "This article proposes some simplifications of the residual variance estimator of Gasser, Sroka, and jennen-Steinmetz (GSJ, 1986) which is often used in conjunction with nonparametric regression. The GSJ estimator is a quadratic form of the data, which depends on the relative spacings of the design points. When the errors are independent, identically distributed Gaussian variables, and the true regression curve is flat, theestimate is distributed as a weighted sum of x2 variables. By matching the first two moments, the distribution can be approximated by a x2with degrees of freedom determined by the coefficients of the quadratic for. Computation ofthe estimated degrees of freedom requires computing the trace of the square of an n x n matrix, where n is the number of design points. In this article, (n-2)/3 is shown to be a conservative estimate of the approximate degrees of freedom, and (n-2)/2 is shown to be conservative for many designs. In addition, a simplified version of the estimator is shown to be asymptotically equivalent, under many conditions.",
author = "Altman, {Naomi S.} and Paulson, {C. P.}",
year = "1993",
month = "1",
day = "1",
doi = "10.1080/03610928308831072",
language = "English (US)",
volume = "22",
pages = "1045--1051",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

Some remarks about the gasser-sroka-jennen-steinnietz variance estimator. / Altman, Naomi S.; Paulson, C. P.

In: Communications in Statistics - Theory and Methods, Vol. 22, No. 4, 01.01.1993, p. 1045-1051.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Some remarks about the gasser-sroka-jennen-steinnietz variance estimator

AU - Altman, Naomi S.

AU - Paulson, C. P.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - This article proposes some simplifications of the residual variance estimator of Gasser, Sroka, and jennen-Steinmetz (GSJ, 1986) which is often used in conjunction with nonparametric regression. The GSJ estimator is a quadratic form of the data, which depends on the relative spacings of the design points. When the errors are independent, identically distributed Gaussian variables, and the true regression curve is flat, theestimate is distributed as a weighted sum of x2 variables. By matching the first two moments, the distribution can be approximated by a x2with degrees of freedom determined by the coefficients of the quadratic for. Computation ofthe estimated degrees of freedom requires computing the trace of the square of an n x n matrix, where n is the number of design points. In this article, (n-2)/3 is shown to be a conservative estimate of the approximate degrees of freedom, and (n-2)/2 is shown to be conservative for many designs. In addition, a simplified version of the estimator is shown to be asymptotically equivalent, under many conditions.

AB - This article proposes some simplifications of the residual variance estimator of Gasser, Sroka, and jennen-Steinmetz (GSJ, 1986) which is often used in conjunction with nonparametric regression. The GSJ estimator is a quadratic form of the data, which depends on the relative spacings of the design points. When the errors are independent, identically distributed Gaussian variables, and the true regression curve is flat, theestimate is distributed as a weighted sum of x2 variables. By matching the first two moments, the distribution can be approximated by a x2with degrees of freedom determined by the coefficients of the quadratic for. Computation ofthe estimated degrees of freedom requires computing the trace of the square of an n x n matrix, where n is the number of design points. In this article, (n-2)/3 is shown to be a conservative estimate of the approximate degrees of freedom, and (n-2)/2 is shown to be conservative for many designs. In addition, a simplified version of the estimator is shown to be asymptotically equivalent, under many conditions.

UR - http://www.scopus.com/inward/record.url?scp=84947611135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947611135&partnerID=8YFLogxK

U2 - 10.1080/03610928308831072

DO - 10.1080/03610928308831072

M3 - Article

AN - SCOPUS:84947611135

VL - 22

SP - 1045

EP - 1051

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 4

ER -