Checking for lack of fit in linear models with parametric variance functions

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

I adapt near-replicate lack-of-fit tests for checking the adequacy of a linear model for means to check for lack of fit in a standard log-linear model for variances. A graphical method for checking lack of fit in the variance model is also proposed. In addition, an overall test of lack of fit in means or variances is presented. Three examples are used to illustrate the techniques.

Original languageEnglish (US)
Pages (from-to)226-236
Number of pages11
JournalTechnometrics
Volume42
Issue number3
DOIs
StatePublished - Aug 2000
Externally publishedYes

Keywords

  • Near replicates
  • Omnibus test
  • Regression diagnostics

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Checking for lack of fit in linear models with parametric variance functions'. Together they form a unique fingerprint.

Cite this