EMMEANS Subcommand (MIXED command)
EMMEANS
displays
estimated marginal means of the dependent variable in the cells and
their standard errors for the specified factors. Note that these are
predicted, not observed, means.
- The
TABLES
keyword, followed by an option in parentheses, is required.COMPARE
is optional; if specified, it must followTABLES
. - Multiple
EMMEANS
subcommands are allowed. Each is treated independently. - If identical
EMMEANS
subcommands are specified, only the last identical subcommand is in effect.EMMEANS
subcommands that are redundant but not identical (for example, crossed factor combinations such as A*B and B*A) are all processed.
TABLES(option). Table specification. Valid options are the
keyword OVERALL
, factors appearing
on the factor list, and crossed factors constructed of factors on
the factor list. Crossed factors can be specified by using an asterisk
(*) or the keyword BY
. All factors
in a crossed factor specification must be unique.
- If
OVERALL
is specified, the estimated marginal means of the dependent variable are displayed, collapsing over all factors. - If a factor, or a crossing factor, is specified on
the
TABLES
keyword,MIXED
will compute the estimated marginal mean for each level combination of the specified factor(s), collapsing over all other factors not specified withTABLES
.
WITH (option).
Covariate values. Valid options
are covariates appearing on the covariate list on the VARIABLES
subcommand. Each covariate must
be followed by a numeric value or the keyword MEAN
.
- If a numeric value is used, the estimated marginal mean will be computed by holding the specified covariate at the supplied value.
- When the keyword
MEAN
is used, the estimated marginal mean will be computed by holding the covariate at its overall mean. If a covariate is not specified in theWITH
option, its overall mean will be used in estimated marginal mean calculations.
COMPARE(factor) REFCAT(value) ADJ(method). Main- or simple-main-effects omnibus tests
and pairwise comparisons of the dependent variable. This
option gives the mean difference, standard error, degrees of freedom,
significance, and confidence intervals for each pair of levels for
the effect specified in the COMPARE
keyword, and an omnibus test for that effect. If only one factor
is specified on TABLES
, COMPARE
can be specified by itself; otherwise,
the factor specification is required. In this case, levels of the
specified factor are compared with each other for each level of the
other factors in the interaction.
- The optional
ADJ
keyword allows you to apply an adjustment to the confidence intervals and significance values to account for multiple comparisons. Methods available areLSD
(no adjustment),BONFERRONI
, orSIDAK
. - By default, all pairwise comparisons of the specified
factor will be constructed. Optionally, comparisons can be made to
a reference category by specifying the value of that category after
the
REFCAT
keyword. If the compare factor is a string variable, the category value must be a quoted string. If the compare factor is a numeric variable, the category value should be specified as an unquoted numeric value. Alternatively, the keywordsFIRST
orLAST
can be used to specify whether the first or the last category will be used as a reference category.
Example
MIXED Y BY A B WITH X
/FIXED A B X
/EMMEANS TABLES(A*B) WITH(X=0.23) COMPARE(A) ADJ(SIDAK)
/EMMEANS TABLES(A*B) WITH(X=MEAN) COMPARE(A) REFCAT(LAST) ADJ(LSD).
- In the example, the first
EMMEANS
subcommand will compute estimated marginal means for all level combinations of A*B by fixing the covariate X at 0.23. Then for each level of B, all pairwise comparisons on A will be performed usingSIDAK
adjustment. - In the second
EMMEANS
subcommand, the estimated marginal means will be computed by fixing the covariate X at its mean. SinceREFCAT(LAST)
is specified, comparison will be made to the last category of factor A usingLSD
adjustment.