The GRADAR Procedure

Example 5: Using Multiple Classification Variables in Radar Charts

Procedure features:

ACROSSVAR=

DOWNVAR=

FREQ=

STARTYPE=

NCOLS=

NROWS=

STARLEGEND=

Data set:

FAILURE

Sample library member:

GRRTWOWY

[untitled graphic]

You can study the effects of two classifications simultaneously with a two-way comparative radar chart. This arrangement provides the opportunity to discover both one-way marginal effects and interaction effects. To produce the chart, use both the ACROSSVAR= and DOWNVAR= options.

This example features the following options:

The ACROSSVAR= option specifies variable DAY as the variable whose values determine the rows in the chart matrix.
DOWNVAR= specifies variable PROCESS as the variable whose values determine the columns in the chart matrix.
STARTYPE= determines that the stars are displayed with rays emanating from the inner circle.
NROWS= and NCOLS= specify the number of rows and columns in the chart.
STARLEGEND= CLOCK generates a legend that identifies spoke positions. Value CLOCK determines that the positions are identified using a clock metaphor.

goptions reset=all border;

proc gradar data=failure;
    chart cause / acrossvar=day
        downvar=process
        freq=count
        startype=spoke
        nrows=2 ncols=5
        starlegend=clock;
run;
quit;

Top of Page