PROC MIXED Statements

Enter SAS PROC MIXED statements in this field to override default parameters for the model.

You can specify any PROC MIXED statement except for the PROC, BY, or RUN statements.

PROC MIXED statements are written in the following syntax:

Statement var1...varn;

where:

•

Statement is the PROC MIXED statement,

•

var1...varn are the variables (or specific values) specified,

•

italicized items indicate a variable, or option to be specified,

•

items within the angle brackets are optional,

•

each element in the statement is delimited by a space,

•

the statement ends with a semicolon (;), and

•

each PROC MIXED statement is written on a separate line in the field.

Note: Variables specified here can come from either the adsl.sas7bdat or ae.sas7bdat data sets.

Examples of commonly used PROC MIXED statements are listed in the following table.

Statement	Definition	Syntax
CLASS	names the classification variables to be used in the model	CLASS var1...varn;
MODEL	names a single dependent variable and the fixed effects that determine the X matrix of the model	MODEL Response = <fixed effects>; Note: In the Mixed Model Analysis analytical procedure, the data file and the EDDS are combined into a stacked SAS data set where all of the probe intensity values are combined into a single column that is named Response by default. Your PROC MIXED Model statement must use this variable name, as shown above.
RANDOM	used to specify one or more variables classification or continuous random coefficients	RANDOM random effects;
LSMEANS	computes the least square means for the fixed effects	LSMEANS fixed effects;
REPEATED	specifies the R matrix in the model	REPEATED <repeated effect>;
ESTIMATE	constructs custom scalar estimates for confidence limits	ESTIMATE ‘label’<fixed effect values> <\|random effect values>;

Type specific PROC MIXED statements in the PROC MIXED Statements field.

Refer to the SAS documentation for PROC MIXED for more information.