Generating Random Samples

SAS, EXCEL, JMP, SPSS

 Population of Data  Sample
• Data should be in a dataset where each row
represents an individual unit, and column fields
represent variables measured on the individual
• A new column field will be created that contains
a pseudo-random number generated by statistal
software package (usually Uniform(0,1) r.v.)
• Data are sorted by the random number, or simply
selected for analysis (depending on software)
All ATL/HNL 10/2004 Delta Flights (N=31)
Day FlightNum TailNum DestCity TaxiTime Sched Actual Distance
1 317 N834MH HNL 29 580 567 4496
2 317 N836MH HNL 21 580 582 4496
3 317 N844MH HNL 24 580 592 4496
4 317 N838MH HNL 19 580 601 4496
5 317 N827MH HNL 13 580 567 4496
6 317 N830MH HNL 16 580 585 4496
7 317 N833MH HNL 17 580 569 4496
8 317 N828MH HNL 14 580 568 4496
9 317 N844MH HNL 22 580 569 4496
10 317 N843MH HNL 14 580 553 4496
11 317 N830MH HNL 12 580 531 4496
12 317 N834MH HNL 21 580 538 4496
13 317 N828MH HNL 28 580 545 4496
14 317 N826MH HNL 22 580 542 4496
15 317 N843MH HNL 23 580 558 4496
16 317 N825MH HNL 16 580 558 4496
17 317 N837MH HNL 20 580 579 4496
18 317 N838MH HNL 26 580 584 4496
19 317 N844MH HNL 17 580 583 4496
20 317 N826MH HNL 28 580 582 4496
21 317 N831MH HNL 17 580 577 4496
22 317 N845MH HNL 20 580 582 4496
23 317 N843MH HNL 17 580 583 4496
24 317 N829MH HNL 22 580 596 4496
25 317 N839MH HNL 19 580 589 4496
26 317 N830MH HNL 16 580 586 4496
27 317 N844MH HNL 18 580 567 4496
28 317 N834MH HNL 27 580 582 4496
29 317 N835MH HNL 61 580 627 4496
30 317 N830MH HNL 14 580 580 4496
31 317 N840MH HNL 16 580 576 4496
SAS Code to Generate Random Sample (n=10)
Data Pop;
Input Day FlightNum TailNum $ DestCity $ TaxiTime Sched
Actual Distance;
Ranx=Ranuni(seed); /* Put in a number where “seed” is */
Cards;
1 317 N834MH HNL 29 580 567 4496
…
31 317 N840MH HNL 16 580 576 4496
;
Proc Sort; By Ranx;
Data Sample;
Set Pop;
If _N_ <= 10;
Run;
/* You can run any procedures now on the Sample */
 Generating Random Samples in EXCEL
• In a new column past the data, type in the first row
containing data on a unit: =RAND()
• COPY and PASTE that cell until all N units have a
random number
• While that range of N cells is still highlighted, click on
COPY  EDIT  PASTE SPECIAL  Click on
VALUES (This changes them from Dynamic to Static)
• Place Cursor in Data Field, Click on: DATA  SORT 
Choose Column with Random Values and Choose
appropriate Header Row Status
• After data are sorted, COPY and PASTE (SPECIAL
VALUES) the first n units to a new worksheet
Day FlightNum TailNum DestCity TaxiTime Sched Actual Distance RANX
1 317 N834MH HNL 29 580 567 4496 0.350812
2 317 N836MH HNL 21 580 582 4496 0.752161
3 317 N844MH HNL 24 580 592 4496 0.187453
4 317 N838MH HNL 19 580 601 4496 0.188703
5 317 N827MH HNL 13 580 567 4496 0.460054
6 317 N830MH HNL 16 580 585 4496 0.400567
7 317 N833MH HNL 17 580 569 4496 0.182854
8 317 N828MH HNL 14 580 568 4496 0.021221
9 317 N844MH HNL 22 580 569 4496 0.626882
10 317 N843MH HNL 14 580 553 4496 0.816402
11 317 N830MH HNL 12 580 531 4496 0.098956
12 317 N834MH HNL 21 580 538 4496 0.055447 Random
13 317 N828MH HNL 28 580 545 4496 0.758031
14 317 N826MH HNL 22 580 542 4496 0.832901 Numbers
15 317 N843MH HNL 23 580 558 4496 0.128992
16 317 N825MH HNL 16 580 558 4496 0.038679 (Not Sorted
17 317 N837MH HNL 20 580 579 4496 0.079991
18 317 N838MH HNL 26 580 584 4496 0.799248 Yet)
19 317 N844MH HNL 17 580 583 4496 0.622701
20 317 N826MH HNL 28 580 582 4496 0.759538
21 317 N831MH HNL 17 580 577 4496 0.630077
22 317 N845MH HNL 20 580 582 4496 0.197023
23 317 N843MH HNL 17 580 583 4496 0.175767
24 317 N829MH HNL 22 580 596 4496 0.42
25 317 N839MH HNL 19 580 589 4496 0.03482
26 317 N830MH HNL 16 580 586 4496 0.183414
27 317 N844MH HNL 18 580 567 4496 0.518784
28 317 N834MH HNL 27 580 582 4496 0.185114
29 317 N835MH HNL 61 580 627 4496 0.220694
30 317 N830MH HNL 14 580 580 4496 0.643347
31 317 N840MH HNL 16 580 576 4496 0.522772
Day FlightNum TailNum DestCity TaxiTime Sched Actual Distance RANX
8 317 N828MH HNL 14 580 568 4496 0.021221
25 317 N839MH HNL 19 580 589 4496 0.03482
16 317 N825MH HNL 16 580 558 4496 0.038679
12 317 N834MH HNL 21 580 538 4496 0.055447
17 317 N837MH HNL 20 580 579 4496 0.079991
11 317 N830MH HNL 12 580 531 4496 0.098956
15 317 N843MH HNL 23 580 558 4496 0.128992
23 317 N843MH HNL 17 580 583 4496 0.175767
7 317 N833MH HNL 17 580 569 4496 0.182854
26 317 N830MH HNL 16 580 586 4496 0.183414
28 317 N834MH HNL 27 580 582 4496 0.185114
3
4
317
317
N844MH
N838MH
HNL
HNL
24
19
580
580
592
601
4496
4496
0.187453
0.188703
Data
22
29
317
317
N845MH
N835MH
HNL
HNL
20
61
580
580
582
627
4496
4496
0.197023
0.220694
Sorted
1 317 N834MH HNL 29 580 567 4496 0.350812 By
6 317 N830MH HNL 16 580 585 4496 0.400567
24 317 N829MH HNL 22 580 596 4496 0.42 Random
5 317 N827MH HNL 13 580 567 4496 0.460054
27 317 N844MH HNL 18 580 567 4496 0.518784 Number
31 317 N840MH HNL 16 580 576 4496 0.522772
19 317 N844MH HNL 17 580 583 4496 0.622701
9 317 N844MH HNL 22 580 569 4496 0.626882
21 317 N831MH HNL 17 580 577 4496 0.630077
30 317 N830MH HNL 14 580 580 4496 0.643347
2 317 N836MH HNL 21 580 582 4496 0.752161
13 317 N828MH HNL 28 580 545 4496 0.758031
20 317 N826MH HNL 28 580 582 4496 0.759538
18 317 N838MH HNL 26 580 584 4496 0.799248
10 317 N843MH HNL 14 580 553 4496 0.816402
14 317 N826MH HNL 22 580 542 4496 0.832901
 EXCEL Random Sample (n=10)
Day FlightNum TailNum DestCity TaxiTime Sched Actual Distance RANX
8 317 N828MH HNL 14 580 568 4496 0.021221
25 317 N839MH HNL 19 580 589 4496 0.03482
16 317 N825MH HNL 16 580 558 4496 0.038679
12 317 N834MH HNL 21 580 538 4496 0.055447
17 317 N837MH HNL 20 580 579 4496 0.079991
11 317 N830MH HNL 12 580 531 4496 0.098956
15 317 N843MH HNL 23 580 558 4496 0.128992
23 317 N843MH HNL 17 580 583 4496 0.175767
7 317 N833MH HNL 17 580 569 4496 0.182854
26 317 N830MH HNL 16 580 586 4496 0.183414
 Random Samples in JMP

• Import Data into JMP

• Click on TABLES  SUBSET  RANDOM
SAMPLE  Enter Your Sample Size (e.g. 10) in Box
• Subset Dataset Appears in New Table
• Analyze the Data in that Table
 Random Samples in SPSS
• Import Data into SPSS
• Older Versions: Click Transform  Random # Seed
 Enter a numeric seed
• Newer Versions: Click Transform  Random #
Generators  Active Generator Initialization 
Fixed Value  Enter a numeric seed
– Click Data  Select Cases
– Under Select, choose Random Sample of Cases. Click on
Sample box.
– Choose Exactly n (10) of the first N (31), click Continue
– Click OK. Slashes will appear in the case numbers of the cases
not in the sample, and an indicator variable representing Filter
will be attached to end of dataset.
– Analyze the Data