Average-width optimality for confidence bands in simple linear regression

Research output: Contribution to journalArticle

9 Scopus citations

Abstract

The problem of constructing optimal confidence bands for a simple linear regression over the whole real line is considered. Optimality is defined as minimization of the average width of the bands weighted by a normalized function. This weight function is presented as an indicator of experimental interest in the varying width of the band. A comparison between the commonly seen hyperbolic bands and segmented-line bands is presented.

Original languageEnglish (US)
Pages (from-to)692-697
Number of pages6
JournalJournal of the American Statistical Association
Volume80
Issue number391
DOIs
StatePublished - Sep 1985
Externally publishedYes

    Fingerprint

Keywords

  • Constrained minimization
  • Prior weight functions
  • Simultaneous confidence intervals

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this