Effects of Continuous Variables (MANOVA: Univariate command)
Usually you name factors but not covariates on
the DESIGN
subcommand. The linear
effects of covariates are removed from the dependent variable before
the design is tested. However, the design can include variables that
are measured at the interval level and originally named as covariates
or as additional dependent variables.
- Continuous variables on a
DESIGN
subcommand must be named as dependents or covariates on theMANOVA
variable list. - Before you can name a continuous variable on a
DESIGN
subcommand, you must supply anANALYSIS
subcommand that does not name the variable. This action excludes it from the analysis as a dependent variable or covariate and makes it eligible for inclusion onDESIGN
. - You can use the keyword
POOL(varlist)
to pool more than one continuous variable into a single effect (provided that the continuous variables are all excluded on anANALYSIS
subcommand). For a single continuous variable, POOL(VAR) is equivalent to VAR. - The
TO
convention in the variable list forPOOL
refers to the order of continuous variables (dependent variables and covariates) on the originalMANOVA
variable list, which is not necessarily their order on the active dataset. This use is the only allowable use of the keywordTO
on aDESIGN
subcommand. - You can specify interaction terms between factors
and continuous variables. If FAC is a factor and COV is a covariate
that has been omitted from an
ANALYSIS
subcommand, FAC BY COV is a valid specification on aDESIGN
statement. - You cannot specify an interaction between two continuous
variables. Use the
COMPUTE
command to create a variable representing the interaction prior toMANOVA
.
Example
* This example tests whether the regression of the dependent
variable Y on the two variables X1 and X2 is the same across
all the categories of the factors AGE and TREATMNT.
MANOVA Y BY AGE(1,5) TREATMNT(1,3) WITH X1, X2
/ANALYSIS = Y
/DESIGN = POOL(X1,X2),
AGE, TREATMNT, AGE BY TREATMNT,
POOL(X1,X2) BY AGE + POOL(X1,X2) BY TREATMNT
+ POOL(X1,X2) BY AGE BY TREATMNT.
-
ANALYSIS
excludes X1 and X2 from the standard treatment of covariates so that they can be used in the design. -
DESIGN
includes five terms. POOL(X1,X2), the overall regression of the dependent variable on X1 and X2, is entered first, followed by the two factors and their interaction. - The last term is the test for equal regressions. It consists of three factor-by-continuous-variable interactions pooled together. POOL(X1,X2) BY AGE is the interaction between AGE and the combined effect of the continuous variables X1 and X2. It is combined with similar interactions between TREATMNT and the continuous variables and between the AGE by TREATMNT interaction and the continuous variables.
- If the last term is not statistically significant, there is no evidence that the regression of Y on X1 and X2 is different across any combination of the categories of AGE and TREATMNT.