lmerTest (version 2.0-33)

lsmeans: Calculates Least Squares Means and Confidence Intervals for the factors of a fixed part of mixed effects model of lmer object.

Description

Produces a data frame which resembles to what SAS software gives in proc mixed statement. The approximation of degrees of freedom is Satterthwate's. This is a deprecated function, use lsmeansLT function instead.

Usage

lsmeans(model, test.effs = NULL, ddf="Satterthwaite",  ...)

Arguments

model

linear mixed effects model (lmer object).

test.effs

charachter vector specyfying the names of terms to be tested. If NULL all the terms are tested.

ddf

By default the Satterthwaite's approximation to degrees of freedom is calculated. If ddf="Kenward-Roger", then the Kenward-Roger's approximation is calculated using KRmodcomp function from pbkrtest package. If ddf="lme4" then the anova table that comes from lme4 package is returned

…

other potential arguments.

Value

Produces Least Squares Means (population means) table with p-values and Confidence intervals.

References

doBy package, gplots package

See Also

step, rand, lsmeansLT, difflsmeans

Examples

# NOT RUN {

## import lme4 package and lmerTest package
library(lmerTest)

## specify lmer model
m1 <- lmer(Informed.liking ~ Gender*Information +(1|Consumer), data=ham)

# }
# NOT RUN {
## calculate least squares means for interaction Gender:Information
lsmeans(m1, test.effs="Gender:Information")
m <- lmer(Coloursaturation ~ TVset*Picture + (1|Assessor), data=TVbo)
plot(lsmeans(m))
lsmeans(m, test.effs="TVset")
# }