Skip to Main content Skip to Navigation
Conference papers

Modelling finger force produced from different tasks using linear mixed models with the lme R function

Caroline Bazzoli 1 Frédérique Letué 1 Marie-José Martinez 2
1 SAM - Statistique Apprentissage Machine
LJK - Laboratoire Jean Kuntzmann
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
Abstract : In experimental sciences, analysis of variance (ANOVA) is commonly used to explain one continuous response with respect to different experimental conditions, assuming independent observations and homoscedastic errors. In studies where individuals contribute more than one observation, such as longitudinal or repeated-measures studies, the linear mixed model provides then a better framework as an alternative to classical ANOVA. The data considered in this paper have been obtained from a biomechanical study carried out to understand the coordination patterns of finger forces produced from different tasks corresponding to different experimental conditions. This data cannot be considered independent because of within-subject repeated measurements, and because of simultaneous finger measurements. To fit these data, we propose a methodology focused on linear mixed models. Different random effects structures and different residual variance-covariance matrices are considered. We highlight how to use the lme R function to deal with such a complex modelling approach.
Complete list of metadata
Contributor : Marie-José Martinez Connect in order to contact the contributor
Submitted on : Friday, March 6, 2015 - 2:07:34 PM
Last modification on : Tuesday, May 3, 2022 - 3:13:44 AM


  • HAL Id : hal-01126631, version 1


Caroline Bazzoli, Frédérique Letué, Marie-José Martinez. Modelling finger force produced from different tasks using linear mixed models with the lme R function. ERCIM 2014 - 7th International Conference of the ERCIM Working Group on Computational and Methodological Statistics, Dec 2014, Pise, Italy. ⟨hal-01126631⟩



Record views