Simulation-based simultaneous confidence bands in multiple linear regression with predictor variables constrained in intervals

W. Liu, M. Jamshidian, Ying Zhang, J. Donnelly

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

This article presents a method for the construction of a simultaneous confidence band for the normal-error multiple linear regression model. The confidence bands considered have their width proportional to the standard error of the estimated regression function, and the predictor variables are allowed to be constrained in intervals. Past articles in this area gave exact bands only for the simple regression model. When there is more than one predictor variable, only conservative bands are proposed in the statistics literature. This article advances this methodology by providing simulation-based confidence bands for regression models with any number of predictor variables. Additionally, a criterion is proposed to assess the sensitivity of a simultaneous confidence band. This criterion is defined to be the probability that a false linear regression model is excluded from the band at least at one point and hence this false linear regression model is correctly declared as a false model by the band. Finally, the article considers and compares several computational algorithms for obtaining the confidence band.

Original languageEnglish (US)
Pages (from-to)459-484
Number of pages26
JournalJournal of Computational and Graphical Statistics
Volume14
Issue number2
DOIs
StatePublished - Jun 1 2005
Externally publishedYes

Fingerprint

Simultaneous Confidence Bands
Multiple Linear Regression
Confidence Bands
Predictors
Linear Regression Model
Interval
Regression Model
Simulation
Computational Algorithm
Regression Function
Standard error
Directly proportional
Statistics
Multiple linear regression
Confidence
Methodology
False
Linear regression model

Keywords

  • Inequality constraints
  • Linear regression
  • Polyhedral cone
  • Projection
  • Quadratic programming
  • Statistical simulation

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Discrete Mathematics and Combinatorics

Cite this

Simulation-based simultaneous confidence bands in multiple linear regression with predictor variables constrained in intervals. / Liu, W.; Jamshidian, M.; Zhang, Ying; Donnelly, J.

In: Journal of Computational and Graphical Statistics, Vol. 14, No. 2, 01.06.2005, p. 459-484.

Research output: Contribution to journalArticle

@article{538bed114ed84a6b9db9172a3e7c65bd,
title = "Simulation-based simultaneous confidence bands in multiple linear regression with predictor variables constrained in intervals",
abstract = "This article presents a method for the construction of a simultaneous confidence band for the normal-error multiple linear regression model. The confidence bands considered have their width proportional to the standard error of the estimated regression function, and the predictor variables are allowed to be constrained in intervals. Past articles in this area gave exact bands only for the simple regression model. When there is more than one predictor variable, only conservative bands are proposed in the statistics literature. This article advances this methodology by providing simulation-based confidence bands for regression models with any number of predictor variables. Additionally, a criterion is proposed to assess the sensitivity of a simultaneous confidence band. This criterion is defined to be the probability that a false linear regression model is excluded from the band at least at one point and hence this false linear regression model is correctly declared as a false model by the band. Finally, the article considers and compares several computational algorithms for obtaining the confidence band.",
keywords = "Inequality constraints, Linear regression, Polyhedral cone, Projection, Quadratic programming, Statistical simulation",
author = "W. Liu and M. Jamshidian and Ying Zhang and J. Donnelly",
year = "2005",
month = "6",
day = "1",
doi = "10.1198/106186005X47408",
language = "English (US)",
volume = "14",
pages = "459--484",
journal = "Journal of Computational and Graphical Statistics",
issn = "1061-8600",
publisher = "American Statistical Association",
number = "2",

}

TY - JOUR

T1 - Simulation-based simultaneous confidence bands in multiple linear regression with predictor variables constrained in intervals

AU - Liu, W.

AU - Jamshidian, M.

AU - Zhang, Ying

AU - Donnelly, J.

PY - 2005/6/1

Y1 - 2005/6/1

N2 - This article presents a method for the construction of a simultaneous confidence band for the normal-error multiple linear regression model. The confidence bands considered have their width proportional to the standard error of the estimated regression function, and the predictor variables are allowed to be constrained in intervals. Past articles in this area gave exact bands only for the simple regression model. When there is more than one predictor variable, only conservative bands are proposed in the statistics literature. This article advances this methodology by providing simulation-based confidence bands for regression models with any number of predictor variables. Additionally, a criterion is proposed to assess the sensitivity of a simultaneous confidence band. This criterion is defined to be the probability that a false linear regression model is excluded from the band at least at one point and hence this false linear regression model is correctly declared as a false model by the band. Finally, the article considers and compares several computational algorithms for obtaining the confidence band.

AB - This article presents a method for the construction of a simultaneous confidence band for the normal-error multiple linear regression model. The confidence bands considered have their width proportional to the standard error of the estimated regression function, and the predictor variables are allowed to be constrained in intervals. Past articles in this area gave exact bands only for the simple regression model. When there is more than one predictor variable, only conservative bands are proposed in the statistics literature. This article advances this methodology by providing simulation-based confidence bands for regression models with any number of predictor variables. Additionally, a criterion is proposed to assess the sensitivity of a simultaneous confidence band. This criterion is defined to be the probability that a false linear regression model is excluded from the band at least at one point and hence this false linear regression model is correctly declared as a false model by the band. Finally, the article considers and compares several computational algorithms for obtaining the confidence band.

KW - Inequality constraints

KW - Linear regression

KW - Polyhedral cone

KW - Projection

KW - Quadratic programming

KW - Statistical simulation

UR - http://www.scopus.com/inward/record.url?scp=13444255042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13444255042&partnerID=8YFLogxK

U2 - 10.1198/106186005X47408

DO - 10.1198/106186005X47408

M3 - Article

VL - 14

SP - 459

EP - 484

JO - Journal of Computational and Graphical Statistics

JF - Journal of Computational and Graphical Statistics

SN - 1061-8600

IS - 2

ER -