I am trying to run a linear mixed effects model similar to the 2*2*2 anova design. My DV is reaction time and fixed factors are time (pre vs. post:within-subject), condition (congruent vs. incongruent: within subject) and stimulation (vertex vs. DLPFC: between subject) My concerns are: a)I have very few participants: 7 in the vertex condition and 7 in the DLPFC condition. b)2 out of the 7 participants participated in both vertex and DLPFC condition. How do I compute a nested lmer model with reaction time as DV and time, condition and stimulation as factors? and how do i account for random intercepts and slopes with few number of participants? Thanks for all the help -- View this message in context: http://r.789695.n4.nabble.com/equivalent-of-repeated-measures-anova-using-lmer-tp4711265.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]]
asudar <aruna.sudarshan <at> gmail.com> writes:> > I am trying to run a linear mixed effects model similar to the 2*2*2 anova > design. My DV is reaction time and fixed factors are time (pre vs. > post:within-subject), condition (congruent vs. incongruent: within subject) > and stimulation (vertex vs. DLPFC: between subject) > My concerns are: > a)I have very few participants: 7 in the vertex condition and 7 in the > DLPFC condition. > b)2 out of the 7 participants participated in both vertex and DLPFC > condition. > How do I compute a nested lmer model with reaction time as DV and time, > condition and stimulation as factors? and how do i account for random > intercepts and slopes with few number of participants? > Thanks for all the helpYou'll probably get more useful answers to this question on the r-sig-mixed-models at r-project.org mailing list. 7 participants is small but doesn't seem horribly small (but it might preclude estimating a full random-slopes model). You'll get more information on r-sig-mixed-models ...