Probability

Probability Sampling
Sampling
 Types of Probability Sampling
Sampling
Designs
Designs

Simple random sampling

Stratified sampling

Systematic sampling

Cluster (area) sampling

Multistage sampling
 Some Definitions


N = the number of cases in the
sampling frame

n = the number of cases in the sample
NCn = the number of combinations


(subsets) of n from N

f = n/N = the sampling fraction
Simple
Simple Random
Random Sampling
Sampling

• Objective: Select n units out of N such

that every NCn has an equal chance.
• Procedure: Use table of random numbers,
computer random number generator or
mechanical device.
• Can sample with or without replacement.
• f=n/N is the sampling fraction.
 Simple
Simple Random
Random Sampling
Sampling
Example:

Small service agency.

Client assessment of quality of service.

Get list of clients over past year.

Draw a simple random sample of n/N.
Simple
Simple Random
Random Sampling
Sampling

List of clients
Simple
Simple Random
Random Sampling
Sampling

List of clients

Random subsample
Stratified
Stratified Random
Random Sampling
Sampling

• Sometimes called "proportional" or

"quota" random sampling.
• Objective: Population of N units
divided into nonoverlapping strata
N1, N2, N3, ... Ni such that N1 + N2
+ ... + Ni = N; then do simple random
sample of n/N in each strata.
 Stratified
Stratified Sampling
Sampling -- Purposes:
Purposes:
• To insure representation of each
strata, oversample smaller population
groups.
• Administrative convenience -- field
offices.
• Sampling problems may differ in each
strata.
• Increase precision (lower variance) if
strata are homogeneous within (like
blocking).
Stratified
Stratified Random
Random Sampling
Sampling

List of clients
 Stratified
Stratified Random
Random Sampling
Sampling

List of clients

African-American Hispanic-American Others

Strata
 Stratified
Stratified Random
Random Sampling
Sampling

List of clients

African-American Hispanic-American Others

Strata

Random subsamples of n/N

 Proportionate
Proportionate vs.
vs. Disproportionate
Disproportionate Stratified
Stratified
Random
Random Sampling
Sampling


Proportionate: If sampling fraction is
equal for each stratum

Disproportionate: Unequal sampling
fraction in each stratum

Needed to enable better representation
of smaller (minority groups)
 Systematic
Systematic Random Sampling
Procedure:

Number units in population from 1 to N.

Decide on the n that you want or need.

N/n=k the interval size.

Randomly select a number from 1 to k.

Take every kth unit.
 Systematic
Systematic Random Sampling


Assumes that the population is
randomly ordered.

Advantages: Easy; may be more
precise than simple random sample.

Example: The library (ACM) study.
Systematic
Systematic Random Sampling
1 26 51 76
2 27 52 77
3 28 53 78
N = 100 4 29 54 79
5 30 55 80
6 31 56 81
7 32 57 82
8 33 58 83
9 34 59 84
10 35 60 85
11 36 61 86
12 37 62 87
13 38 63 88
14 39 64 89
15 40 65 90
16 41 66 91
17 42 67 92
18 43 68 93
19 44 69 94
20 45 70 95
21 46 71 96
22 47 72 97
23 48 73 98
24 49 74 99
25 50 75 100
Systematic
Systematic Random Sampling
1 26 51 76
2 27 52 77
3 28 53 78
N = 100 4 29 54 79
5 30 55 80
6 31 56 81
7 32 57 82
Want n = 20 8 33 58 83
9 34 59 84
10 35 60 85
11 36 61 86
12 37 62 87
13 38 63 88
14 39 64 89
15 40 65 90
16 41 66 91
17 42 67 92
18 43 68 93
19 44 69 94
20 45 70 95
21 46 71 96
22 47 72 97
23 48 73 98
24 49 74 99
25 50 75 100
Systematic
Systematic Random Sampling
1 26 51 76
2 27 52 77
3 28 53 78
N = 100 4 29 54 79
5 30 55 80
6 31 56 81
7 32 57 82
want n = 20 8 33 58 83
9 34 59 84
10 35 60 85
11 36 61 86
N/n = 5 12 37 62 87
13 38 63 88
14 39 64 89
15 40 65 90
16 41 66 91
17 42 67 92
18 43 68 93
19 44 69 94
20 45 70 95
21 46 71 96
22 47 72 97
23 48 73 98
24 49 74 99
25 50 75 100
 Systematic
Systematic Random Sampling
1 26 51 76
2 27 52 77
3 28 53 78
N = 100 4 29 54 79
5 30 55 80
6 31 56 81
7 32 57 82
Want n = 20 8 33 58 83
9 34 59 84
10 35 60 85
11 36 61 86
N/n = 5 12 37 62 87
13 38 63 88
14 39 64 89
15 40 65 90
Select a random number from 1-5: 16 41 66 91
17 42 67 92
chose 4 18 43 68 93
19 44 69 94
20 45 70 95
21 46 71 96
22 47 72 97
23 48 73 98
24 49 74 99
25 50 75 100
 Systematic
Systematic Random Sampling
1 26 51 76
2 27 52 77
3 28 53 78
N = 100 4 29 54 79
5 30 55 80
6 31 56 81
7 32 57 82
Want n = 20 8 33 58 83
9 34 59 84
10 35 60 85
11 36 61 86
N/n = 5 12 37 62 87
13 38 63 88
14 39 64 89
15 40 65 90
Select a random number from 1-5: 16 41 66 91
17 42 67 92
chose 4 18 43 68 93
19 44 69 94
20 45 70 95
21 46 71 96
22 47 72 97
Start with #4 and take every 5th unit 23 48 73 98
24 49 74 99
25 50 75 100
 Cluster
Cluster (Area)
(Area) Random
Random Sampling
Sampling

Procedure:

Divide population into clusters.

Randomly sample clusters.

Measure all units within sampled
clusters.
 Cluster
Cluster (Area)
(Area) Random
Random Sampling
Sampling


Advantages: Administratively useful,
especially when you have a wide
geographic area to cover.


Examples: Randomly sample from city
blocks and measure all homes in
selected blocks.
 Multi-Stage
Multi-Stage Sampling
Sampling


Cluster (area) random sampling can be
multi-stage.

Any combinations of single-stage
methods.
 Multi-Stage
Multi-Stage Sampling
Sampling
Example: Choosing students from schools

Select all schools; then sample within
schools.

Sample schools; then measure all
students.

Sample schools; then sample students.