Simulated data set with split plot design
Simulated lexical decision latencies with priming as treatment and reaction time in lexical decision as dependent variable.
data(splitplot)
A data frame with 800 observations on the following 11 variables.
itemsA factor with levels w1, w2,
..., w40, coding 40 word items.
ritemsThe by-word random adjustments to the intercept.
listA factor with levels listA and listB.
The priming effect is counterbalanced for subjects across these
two lists, compare table(splitplot$list, splitplot$subjects).
rlistThe by-list random adjustments to the intercept.
primingA treatment factor with levels primed and
unprimed.
fprimingThe priming effect, -30 for the primed and 0 for the unprimed condition.
subjectsA factor with levels s1, s2,
... s20 coding 20 subjects.
rsubjectThe by-subject random adjustments to the intercept.
errorThe by-observation noise.
intThe intercept.
RTThe reaction time.
R. H. Baayen, D. J. Davidson and D. M. Bates. Mixed-effects modeling with crossed random effects for subjects and items. Manuscript under revision for Journal of Memory and Language.
## Not run: data(splitplot) table(splitplot$list, splitplot$subjects) dat=splitplot require(lme4) require(optimx) require(lmerTest) dat.lmer1 = lmer(RT ~ list*priming+(1+priming|subjects)+(1+list|items),data=dat, control=lmerControl(optimizer="optimx",optCtrl=list(method="nlminb"))) dat.lmer2 = lmer(RT ~ list*priming+(1+priming|subjects)+(1|items),data=dat, control=lmerControl(optimizer="optimx",optCtrl=list(method="nlminb"))) dat.lmer3 = lmer(RT ~ list*priming+(1|subjects)+(1|items),data=dat, control=lmerControl(optimizer="optimx",optCtrl=list(method="nlminb"))) dat.lmer4 = lmer(RT ~ list*priming+(1|subjects),data=dat, control=lmerControl(optimizer="optimx",optCtrl=list(method="nlminb"))) anova(dat.lmer1, dat.lmer2, dat.lmer3, dat.lmer4) summary(dat.lmer3) ## End(Not run)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.