Skip to Main content Skip to Navigation
Journal articles

Modelling repeated paired phonetic measures using linear mixed models with correlated errors

Abstract : In Phonetic Sciences, statistical analysis from experimental data have to be carried out to confirm or disconfirm hypotheses. In this paper, a phonetic data set is considered and phonetic research questions are addressed. To answer these questions, a mixed model is built using a complex random effects structure and a non-diagonal residual variance-covariance matrix. Then, it is validated on the data. Finally, we focus on statistical tests in the final model allowing to compare the means between two groups of subjects, and a single mean to a reference value. The paper is accessible to an audience experienced with linear models. Some familiarity with the R software is also helpful.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03235741
Contributor : Frédérique Letué <>
Submitted on : Wednesday, May 26, 2021 - 12:03:53 AM
Last modification on : Wednesday, June 16, 2021 - 2:30:53 PM

Identifiers

  • HAL Id : hal-03235741, version 1

Citation

Frédérique Letué, Marie-José Martinez, Sandra Cornaz, Nathalie Vallée, Nathalie Henrich Bernardoni. Modelling repeated paired phonetic measures using linear mixed models with correlated errors. Case Studies in Business, Industry and Government Statistics, Société Française de Statistique, 2021, 8, pp.28-46. ⟨hal-03235741⟩

Share

Metrics

Record views

52