Hi, Thank you for the replies.
Yes I would say it does resemble a randomized block design in that each person completed 4 out of a possible 16 versions/conditions of the vignette. There was approximately 20 responses in each condition. The commands I have been using are; modela <-lmer(DV ~ IV*IV*IV*IV + Co-variate + Co-variate + (1|Subject)) anova(modela). I have been working out the denominator degrees of freedom myself at the minute, just for reporting. Do you mean I should use the df and look up in F critical value table rather than use pMCMC bbolker? Robert I see what you mean, some of my hypotheses are two tailed, so for these F < 1 is a signficant finding, just in the other direction. For my one tailed hypotheses then a value of less than 1 would not be signficant? Thanks again it is really helpful as most of the lecturers in my university are familiar with SPSS and use R very rarely. -- View this message in context: http://r.789695.n4.nabble.com/Using-MCMC-sampling-to-estimate-p-values-with-a-mixed-model-tp3606654p3611453.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ 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.