As summarized previously, PROC PRINCOMP performs a principal component analysis of interval-scaled data. PROC CORRESP performs correspondence analysis, which is a weighted form of principal component analysis that is appropriate for frequency data. If your data are categorical, use PROC CORRESP instead of PROC PRINCOMP. Both procedures produce an output data set that can be used with the %PLOTIT macro. The plots produced from the PROC CORRESP output data set graphically show relationships among the categories of the categorical variables .