I am doing post-hoc comparisons of contrasts based on linear mixed models I built in R. I am using the emmeans package for the comparisons. One of the default adjustment methods for multiple correction is "mvt" which stands for "multivariate $t$". However, I cannot find a good explanantion of this method. Is there a paper available I can cite?

  • $\begingroup$ I'd recommend expanding the question a little. Say, for example, what mvt stands for (it can be found in the documentation/vignettes and help files of the package). Include the explanations that the authors offers (see here, for example) as a quote so that all readers are on the same page. Don't expect that readers here will google the terms and the package on their own. $\endgroup$ – COOLSerdash Dec 13 '18 at 9:27
  • $\begingroup$ Simply put, the method estimates a multivariate t distribution of all your hypotheses which it uses to generate p-values. The multivariate approach takes into consideration the correlation of the hypotheses. $\endgroup$ – user2974951 Dec 14 '18 at 8:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.