Dear list members, I get the following error when using the glht function to perform a post hoc analysis for an ANOVA with repeated measures:
require(nlme) lme_H2H_musicians = lme(H2H ~ Emotion*Material, data=musicians, random = ~1|Subject) require(multcomp) summary(glht(lme_H2H_musicians, linfct=mcp(Type = "Tukey")), test = adjusted(type = "bonferroni")) Error in mcp2matrix(model, linfct = linfct) : Variable(s) 'Type' have been specified in 'linfct' but cannot be found in 'model'! I don´t understand why I get this error, but at the same time I am not an expert at all of R. I can give you some details more about the experimental design I use and what I want to do with the analysis, so maybe there is a problem with the model I am trying to use, and I need some advices. I performed an experiment where some musicians had to walk with 5 different emotions (sad, tender, neutral, happy, aggressive) while listening to 4 types of sounds (metal, wood, gravel, snow) and I want to see if the sound affects the walking pace. I measured for each walk the average time between steps (H2H, i.e. heel-to-heel) Each trial was repeated twice. The table in .csv format can be downloaded here: https://dl.dropbox.com/u/3288659/Results_data_R.csv The ANOVA that I performed before the post hoc test is the following: aov_H2H_musicians = aov(H2H ~ Emotion*Material + Error(Subject/(Emotion*Material)), data=musicians) summary(aov_H2H_musicians) Thanks in advance All the best [[alternative HTML version deleted]]
______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
