The HPBIN Procedure

Example 3.1 Bucket Binning

The following DATA step creates the SAS data set as the input for the example:

data ex12;
   length id 8;
   do id=1 to 1000;
      x1 = ranuni(101);
      x2 = 10*ranuni(201);
      x3 = 100*ranuni(301);
      output;
   end;
run;

The following statements show the basic usage:

proc hpbin data=ex12 output=out numbin=10 bucket ;
   input x1-x3;
run;

proc print data=out(obs=10); run;

PROC HPBIN generates several ODS tables, which are shown in Figure 3 through Figure 4.

Figure 3: PROC HPBIN Binning Information Display

The HPBIN Procedure

Binning Information
Method	Bucket Binning
Number of Bins Specified	10
Number of Variables	3

Figure 4: PROC HPBIN Mapping Table

Mapping
Variable	Binned Variable	Range	Frequency	Proportion
x1	BIN_x1	x1 < 0.0999254969	108	0.10800000
		0.0999254969 <= x1 < 0.1993986319	94	0.09400000
		0.1993986319 <= x1 < 0.2988717668	90	0.09000000
		0.2988717668 <= x1 < 0.3983449018	95	0.09500000
		0.3983449018 <= x1 < 0.4978180367	90	0.09000000
		0.4978180367 <= x1 < 0.5972911716	115	0.11500000
		0.5972911716 <= x1 < 0.6967643066	116	0.11600000
		0.6967643066 <= x1 < 0.7962374415	105	0.10500000
		0.7962374415 <= x1 < 0.8957105765	106	0.10600000
		0.8957105765 <= x1	81	0.08100000
x2	BIN_x2	x2 < 1.0215392099	99	0.09900000
		1.0215392099 <= x2 < 2.0154070426	110	0.11000000
		2.0154070426 <= x2 < 3.0092748753	99	0.09900000
		3.0092748753 <= x2 < 4.003142708	85	0.08500000
		4.003142708 <= x2 < 4.9970105407	109	0.10900000
		4.9970105407 <= x2 < 5.9908783734	98	0.09800000
		5.9908783734 <= x2 < 6.9847462061	100	0.10000000
		6.9847462061 <= x2 < 7.9786140388	94	0.09400000
		7.9786140388 <= x2 < 8.9724818715	112	0.11200000
		8.9724818715 <= x2	94	0.09400000
x3	BIN_x3	x3 < 10.173596707	97	0.09700000
		10.173596707 <= x3 < 20.14299647	97	0.09700000
		20.14299647 <= x3 < 30.112396232	106	0.10600000
		30.112396232 <= x3 < 40.081795994	94	0.09400000
		40.081795994 <= x3 < 50.051195757	102	0.10200000
		50.051195757 <= x3 < 60.020595519	99	0.09900000
		60.020595519 <= x3 < 69.989995281	107	0.10700000
		69.989995281 <= x3 < 79.959395044	92	0.09200000
		79.959395044 <= x3 < 89.928794806	91	0.09100000
		89.928794806 <= x3	115	0.11500000

In this example, PROC HPBIN also generates the output table. The first 10 observations of the table are shown in Figure 5.

Figure 5: First 10 Observations in the Output Table

Obs	BIN_x1	BIN_x2	BIN_x3
1	7	10	4
2	2	1	9
3	9	8	1
4	8	8	10
5	2	8	7
6	1	6	7
7	7	9	6
8	7	5	1
9	1	4	1
10	7	9	1

Last updated: March 06, 2023