The DESIGN function creates a design matrix of zeros and ones from the column vector specified by column-vector. Each unique value of the column vector generates a column of the design matrix. The columns are arranged in the sort order
of the original values. If is the ith sorted value in the column vector, x
, then the ith column of the design matrix contains ones in rows for which x
has the value , and contains zeros elsewhere.
For example, the following statements produce a design matrix for a column vector that contains three unique values. The first column corresponds to the 'A' level, the second column corresponds to the 'B' level, and the third column corresponds to the 'C' level.
x = {C, A, B, B, A, A}; m = design(x); cols = unique(x); print m[colname=cols];
The design matrix that is returned by the DESIGN function corresponds to the GLM parameterization of classification variables as documented in the section "Parameterization of Model Effects" in the SAS/STAT User's Guide. See also the documentation for the DESIGNF function .