See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/346311717

Understanding probability sampling techniques : Simple Random Sampling,

Systematic sampling, Stratified sampling and Cluster sampling

Article · November 2020

CITATION READS

1 5,501

1 author:

Nur Izzah Jamil

Universiti Teknologi MARA Cawangan Negeri Sembilan Kampus Rembau
65 PUBLICATIONS 115 CITATIONS

SEE PROFILE

All content following this page was uploaded by Nur Izzah Jamil on 25 November 2020.

The user has requested enhancement of the downloaded file.

 PROBABILITY SAMPLING TECHNIQUES
Nur Izzah Binti Jamil
Universiti Teknologi MARA

Researchers prefer to use probability sampling techniques to ensure the research findings are valid and
able to make inferences on the population. Researcher needs a sampling frame where the sample is
selected from the population and has equal chance of being selected as a sample. The sample is
selected based on known probability. The probability sampling technique includes

1) Simple random sampling

2) Systematic sampling
3) Stratified sampling
4) Cluster sampling

SIMPLE RANDOM SAMPLING

Sample is selected from population and has equal chance of being selected as a sample. The sample is
taken randomly from a sampling frame. Some common sampling frames include the telephone
directory, customer list and student list.

Steps:

1. Researcher needs a sampling frame.

Example: List of students’ names.

Figure 1. List of students’ names

2. Generated random number to determine which elements are to be selected as a sample through
random number table, Microsoft excel and calculator.

1
RANDOM NUMBERS TABLE

Let’s try using random numbers table. Based on Figure 1, researcher needs 5 students (sample size,
n =5) out of 15 students (population size, N=15). By using the first two column numbers, list down
your 5 selected samples.

TABLE OF RANDOM DIGITS

940 100 857 728

741 056 001 147
628 324 599 339
117 646 871 664
149 065 358 013
660 871 033 002
083 500 358 283
900 861 400 395
088 958 732 107
309 035 287 166

Answer:

11, 14, 8, 10, 5

Hence, the sample corresponding to 11, 14, 8, 10 and 5 will be a sample of 5 obtained from 1 to 15
elements in the population.

2
MICROSOFT EXCEL

Let’s try using Microsoft Excel. Based on Figure 1, researcher needs 5 students (sample size, n =5)
out of 15 students (population size, N=15).

Steps:
1) Type = RANDBETWEEN(1,15) and press Enter. It will generate random number between
1 to 15.

2) Put the cursor at the corner and drag down until you get desire sample size, n.

3
 Drag down from
the corner

3) Hence, the sample corresponding to 11, 13, 3, 14 and 15 will be a sample of 5 obtained
from 1 to 15 elements in the population.

4
CALCULATOR

Let’s try using Calculator. Based on Figure 1, researcher needs 5 students (sample size, n =5) out of
15 students (population size, N=15).

Steps:
1) SHIFT  Ran#  =
2) Press = to generate next random number

5
SYSTEMATIC SAMPLING

In systematic sampling, we divide the population size (N) by the sample size (n) to obtain the range
(k)
N
k
n

Steps:

1. Researcher needs sampling frame.

2. Researcher needs 5 students (sample size, n =5) out of 15 students (population size, N=15).

15
k 3
5

3. Select starting point. Since k = 3, random number between 1 or 2 or 3 will be selected. Type =
RANDBETWEEN(1,3) and press Enter.

4. Let say number 2 is chosen, start with number 2 and take every k = 3.

2
2+k=5
5+k=8
8 + k = 11
11 + k = 14

5. Hence, the sample corresponding to 2, 5, 8, 11 and 14 will be a sample of 5 obtained from 1 to

15 elements in the population.
6
STRATIFIED SAMPLING

Stratified sampling is used when the population is heterogeneous and the sampling frame is available.
This sampling technique involves dividing heterogeneous population into several homogeneous strata
and then taking random sample from these strata.

Divide heterogeneous
population into several
homogeneous strata

Taking random sample from

each strata using Simple
random sampling or
Systematic sampling

EXAMPLE

A manager is interested in studying the job satisfaction level of their staffs. There are 9 staffs in
Administrative department, 5 staffs in Marketing department and 6 staffs in Production department.
Only 12 staffs will be randomly selected as a sample.

Steps

1) Calculate required sample size, n from each strata

Department Population (N) Sample (n)

9
Administrative 9 n1   12  5
20
5
Marketing 5 n2   12  3
20
6
Production 6 n3   12  4
20
Total 20 12

7
2) In this case, the strata were the three department. The staffs are extracted using simple random
or systematic sampling from each department. Let say, use simple random sampling.

3) Hence, the sample corresponding to 1, 9, 6, 8 and 3 will be a sample for Administrative

department. The sample corresponding to 2, 1 and 5 will be a sample for Marketing
department and sample corresponding to 5, 6, 3 and 4 will be a sample for Production
department.

No. Administrative department

1 ADRIEANA BINTI AJMAL
2 DIANA BINTI OTHMAN
3 FARAH BINTI ZAMRI
4 FARAH FARHANAH BINTI AKMAL
5 FARAH IZZATI BINTI ISMAIL
6 MUHAMMAD ZULHAKIM BIN HAMDAN
7 NUR ANIS BINTI KHAIRUL
8 NUR NABILA BINTI RAZALI
9 SYAIDATUL AINA BINTI OTHMAN
8
No Marketing department
1 AFIFAH NAWAR BINTI MOHD ANWAR
2 DANIAL BIN MOHD AIZUDDIN
3 MUHAMMAD AMIR BIN JAMAL
4 MUHAMMAD ALIFF BIN SYUKRI
5 NUR SOFEA BINTI SULEYMAN
No Production department
1 AFIQ ZAFRAN BIN MOHAMAD
2 MUHAMMAD HAFIZI BIN JAMIL
3 NUR AIN BINTI ASFAN
4 NURUL AIN BINTI HALIM
5 NURUL NAJWA BINTI HAZIM
6 NURUL ALIS BINTI KAMIL

9
CLUSTER SAMPLING

o Cluster sampling is used when the population of interest is scattered widely across certain
geographical area and the sampling frame is available.

o Cluster sampling divides the target population into several clusters based on geographical
areas.

o A random sample of clusters is selected based on probability sampling technique such as

simple random sampling to represent the total population. No units from non-selected clusters
are included in the sample because they are represented by those from selected clusters.

o With stratification, we sample from each of the subgroups but in cluster sampling, we sample
from selected subgroups only.

o Cluster sampling is most applicable when sampling frame is not available or incomplete.

Divide the target population into several

clusters.

From the selected clusters;

Use the entire population in cluster 1 and
cluster 4 as sample.
OR;
Select sample from each cluster 1 and 4
through simple random sampling or
systematic sampling.

EXAMPLE

A researcher wants to take a cluster sample from a large state. The state consists of 5 towns. A random
sample of 2 towns is selected.

Steps:

1) Begin by listing all the towns with residential units. Divide the target population (state) into
different clusters (town). These towns may be considered the clusters.

10
 2) A random sample of clusters is selected based on probability sampling technique such as
simple random sampling. Use =randbetween(1,5) and choose 2 random number. Let say
number 1 and 3 are chosen.

3) Then, from the selected clusters

i. Use the entire population in town 1 and 3 as sample, OR

ii. Select sample from each town1 and 3 through simple random sampling or systematic
sampling.

11

View publication stats