Dear list, Please excuse my ignorance, but I'm trying to model some data using the lme package. vot is a numeric response, and condition, location and obs are all categories. This works:
> anova(vot.lme <- lme(vot ~ condition * location * obs,data=mergedCodesL,random= ~1 |patient)) numDF denDF F-value p-value (Intercept) 1 1898 462.7519 <.0001 condition 2 1898 8.4126 0.0002 location 1 12 0.0272 0.8718 obs 2 1898 472.5526 <.0001 condition:location 2 1898 1.0467 0.3513 condition:obs 4 1898 1.0683 0.3706 location:obs 2 1898 9.7067 0.0001 condition:location:obs 4 1898 4.6143 0.0010 If I then would like to do post-hoc testing, I found in the email archives that I could use the glht function of multcomp - something like summary(glht(vot.lme, linfct=mcp(obs = "Tukey"))) However, if I would like to investigate the condition:location:obs - interaction. What do I do then? Best! /Fredrik -- "Life is like a trumpet - if you don't put anything into it, you don't get anything out of it." [[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.