Variable Lists (PLS command)

The command line variable lists specify the dependent variables, any categorical predictors (factors), and any scale predictors (covariates). ALL and TO keywords are supported in all variable lists.

Dependent Variables

A list of one or more dependent variables must be the first specification on the PLS command.

  • Dependent variables can be numeric or string.
  • If a dependent variable is specified more than once, only the last specification is honored for the variable.

MLEVEL Keyword

By default, the measurement level recorded in the data dictionary is honored for dependent variables.

  • The MLEVEL keyword can be specified after the name of any dependent variable to override its dictionary level of measurement. Specify N (nominal), O (ordinal), or S (scale). Note that the PLS procedure does not distinguish between ordinal and nominal dependent variables; it treats both as categorical.
  • If MLEVEL is not specified and no setting is recorded in the data dictionary, then a numeric variable is treated as scale and a string variable is treated as categorical.
  • A string dependent variable may be defined as ordinal or nominal only.
  • MLEVEL applies only to the variable that immediately precedes it in the dependent variable list. For example, Age Income [S] and Age TO Income [S] assign the scale level of measurement to Income only. The keyword ALL followed by a measurement level specification applies that measurement level to all dependent variables.

REFERENCE Keyword

The REFERENCE keyword specifies the value of the dependent variable to use as the reference category for parameter estimation. REFERENCE can be specified after the name of any dependent variables but is honored only for categorical dependent variables. It is silently ignored for scale variables.

  • Specify FIRST, LAST, or a value. If you specify FIRST, the lowest value is treated as the reference category. LAST (the default) treats highest value of the dependent variable as the reference category.
  • If you specify a value it must exist in the data and be consistent with the type and format of the dependent variable. String and formatted (for example, date or time) values must be quoted.
  • REFERENCE applies only to the variable that immediately precedes it in the dependent variable list. The keyword ALL followed by a REFERENCE specification applies that reference category to all categorical dependent variables.

Predictor Variables

  • At least one predictor must be specified.
  • The names of the categorical predictors, if any, must be preceded by the keyword BY. If keyword BY is specified with no factors, then a warning is issued and BY is ignored.
  • The names of the covariates, if any, must be preceded by the keyword WITH. If keyword WITH is specified with no covariates, then a warning is issued and WITH is ignored.
  • Categorical predictor variables can be numeric or string.
  • Covariates must be numeric.
  • If the dependent variable is specified within a categorical predictor list or a covariate list, then it is ignored in the list.
  • All variables specified within a categorical predictor or covariate list must be unique. If duplicate variables are specified within a list, then the duplicates are ignored.
  • If duplicate variables are specified across the predictor lists, then an error is issued.