As noted earlier, you often want statistics
for grouped data. It is possible to crosstabulate frequencies of two
or more variables. For example, census data is typically crosstabulated
with a variable that represents geographical regions.
The simplest
crosstabulation is a two-way table. To create a two-way table, join
two variables with an asterisk (*) in the TABLES statement of a PROC
FREQ step.
Syntax, TABLES statement
for crosstabulation:
TABLES variable-1
*variable-2 <*
... variable-n>;
Here are the options for two-way tables:
-
variable-1 specifies
table rows.
-
variable-2 specifies
table columns.
|
When crosstabulations
are specified, PROC FREQ produces tables with cells that contain the
following frequencies:
-
-
cell percentage of total frequency
-
cell percentage of row frequency
-
cell percentage of column frequency
For example, the following
program creates the two-way table shown below.
proc format;
value wtfmt low-139='< 140'
140-180='140-180'
181-high='> 180';
value htfmt low-64='< 5''5"'
65-70='5''5-10"'
71-high='> 5''10"';
run;
proc freq data=clinic.diabetes;
tables weight*height;
format weight wtfmt. height htfmt.;
run;
Note that the first
variable, Weight, forms the table rows, and the second variable, Height,
forms the columns. Reversing the order of the variables in the TABLES
statement would reverse their positions in the table. Note also that
the statistics are listed in the legend box.