Can we disregard the whole model? Omnibus non-inferiority testing for R2 in multi-variable linear regression and η^2 in ANOVA

Harlan Campbell (Corresponding author), Daniël Lakens

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

Determining a lack of association between an outcome variable and a number of different explanatory variables is frequently necessary in order to disregard a proposed model (i.e., to confirm the lack of a meaningful association between an outcome and predictors). Despite this, the literature rarely offers information about, or technical recommendations concerning, the appropriate statistical methodology to be used to accomplish this task. This paper introduces non-inferiority tests for ANOVA and linear regression analyses, which correspond to the standard widely used F test for η ^ 2 and R 2 , respectively. A simulation study is conducted to examine the Type I error rates and statistical power of the tests, and a comparison is made with an alternative Bayesian testing approach. The results indicate that the proposed non-inferiority test is a potentially useful tool for 'testing the null'.

Original languageEnglish
JournalBritish Journal of Mathematical and Statistical Psychology
VolumeXX
Issue numberXX
DOIs
Publication statusE-pub ahead of print - 13 Feb 2020

Keywords

  • ANOVA
  • equivalence testing
  • F test
  • linear regression
  • non-inferiority testing

Fingerprint Dive into the research topics of 'Can we disregard the whole model? Omnibus non-inferiority testing for R<sup>2</sup> in multi-variable linear regression and η^2 in ANOVA'. Together they form a unique fingerprint.

Cite this