The experimental EFFECT statement names a constructed effect that you can use to specify terms in the MODEL statement. Each constructed effect corresponds to a collection of columns that are referred to using the name you supply. You can specify multiple EFFECT statements, and all EFFECT statements must precede the MODEL statement.

After the keyword EFFECT, the name of the effect is specified. This name must appear in only one EFFECT statement and must not be the name of a variable in the input data set. After an equal sign, the effect-type is specified followed by the list of variables used in defining the effect within parentheses. In SAS 9.2, the QUANTREG procedure supports only spline effects. You can also specify options pertaining to the effect definition after a slash following the variable list. The SPLIT option is always turned on for the QUANTREG procedure. For more details about the syntax with spline effects, see the section Constructed Effects and the EFFECT Statement of Chapter 18, Shared Concepts and Topics.

The QUANTREG procedure supports the regression spline effect. A spline effect expands variables into spline bases whose form depends on the options that you specify. Design matrix columns are generated separately for each of the numeric variables specified, and these columns are collectively referred to by the name that you specify. By default the spline basis generated for each variable is a cubic B-spline basis with three equally spaced knots positioned between the minimum and maximum values of that variable. You can find more details about regression splines and spline bases in the section Constructed Effects and the EFFECT Statement of Chapter 18, Shared Concepts and Topics.