Visualizing Categorical Data: sieve

The sieve macro ( get sieve.sas)

Sieve diagrams for two-way tables

Usage

  proc iml;
  %include iml(sieve);
  run sieve( f, vnames, lnames, title );

Parameters

f

A two-way contingency table, size r x c

vnames

Variable names, a 1x2 character matrix. vnames[,1]=row variable, vnames[,2]=column variable

lnames

Category names, a 2 x max(r,c) character matrix. lnames[1,]=row categories, vnames[2,]=column categories.

title

Plot title

Global variables

filltype

OBS

fill cells in proportion to observed frequencies

OBSP

like OBS, but also write obs. freq. in cell

DEV

fill in proportion to deviations from independence.

EXL

no fill, write expected frequency in cell

EXP

fill in proportion to exp, write expected frequency in cell

margins

''

nothing in margins

TOTALS

row/col totals in margins

font

font for text

colors

Names of two colors to use for the positive and negative residuals. [Default: {BLUE RED}]

Example

proc iml;
   %include iml(sieve);
   vnames = {'Department' 'Sex:Admit' };
   lnames = { 'A' 'B' 'C' 'D' 'E' 'F',
             'M:Yes' 'M:No' 'F:Yes'  'F:No' ' ' ' '};
          /*   Males       Females  */
   table = { 512  313      89   19,
             353  207      17    8,
             120  205     202  391,
             138  279     131  244,
              53  138      94  299,
              22  351      24  317};
   font='hwpsl009';
   title  = 'Berkeley Admissions Data';
   margins = 'TOTALS';
   run sieve(table, vnames, lnames, title );

See also