Title: Linear Mixed Models for Plant Scientists with Asreml-R
Lead Community Sponsor:
Cosponsor: ASA Section: Biometry and Statistical Computing
Community Cosponsor: Statistical Education/Training for Researchers Community
Format: None (Admin Only)
Keywords: R software, random effects, repeated measures and spatial analysis
Session Description: Ticket Required to Attend: Linear mixed models (LMM) extend the traditional linear model by allowing a more flexible specification of the errors (and other random factors). They allows for a different type of inference and also allows to incorporate correlation and heterogeneous variances between the observations. The main aim of this workshop is to train scientists in LMM with the aim of promoting sound scientific research based on good statistical thinking and practice that requires proper use and critical interpretation of the outcomes and coding of the models. In this workshop, illustration with real datasets of analysis of LMM will be presented using ASReml-R, a library from the statistical package R. Theoretical details will be kept to a minimum but several examples will be presented and fully discussed. Some of the aspects to address will include: 1) why fixed or random effects? 2) complex field experiments that require LMM, 3) dealing with unbalanced data, 4) correlation on time: repeated measures, and 5) correlation on space: spatial analysis.