Revistes Publicacions URV: SORT - Statistics and Operations Research Transactions> 2018

Heteroscedasticity irrelevance when testing means difference

  • Identification data

    Identifier: RP:2473
    Handle: https://hdl.handle.net/20.500.11797/RP2473
    Authors:
    Ocaña, JordiFlores, Pablo
    Abstract:
    Heteroscedasticity produces a lack of type I error control in Student’s t test for difference between means. Pretesting for it (e.g., by means of Levene’s test) should be avoided as this also induces type I error. These pretests are inadequate for their objective: not rejecting the null hypotheses is not a proof of homoscedasticity; and rejecting it may simply suggest an irrelevant heteroscedasticity. We propose a method to establish irrelevance limits for the ratio of variances. In conjunction with a test for dispersion equivalence, this appears to be a more affordable pretesting strategy.

  • Others:

    URV's Author/s: Ocaña, Jordi Flores, Pablo
    Keywords: Homoscedasticity, equivalence test, indifference zone, pretest, Student’s t test
    Abstract: Heteroscedasticity produces a lack of type I error control in Student’s t test for difference between means. Pretesting for it (e.g., by means of Levene’s test) should be avoided as this also induces type I error. These pretests are inadequate for their objective: not rejecting the null hypotheses is not a proof of homoscedasticity; and rejecting it may simply suggest an irrelevant heteroscedasticity. We propose a method to establish irrelevance limits for the ratio of variances. In conjunction with a test for dispersion equivalence, this appears to be a more affordable pretesting strategy.
    Journal publication year: 2018
    Publication Type: info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article

  • Keywords:

    Homoscedasticity, equivalence test, indifference zone, pretest, Student’s t test

  • Documents:

    DocumentPrincipal

  • Cerca a google

    Search to google scholar