SAMPLING

Non-Probability sampling technique:

Quota sampling
is a non-probability sampling technique used in research to ensure that specific subgroups within a
population are adequately represented. Researchers divide the population into mutually exclusive
subgroups (quotas) and then select subjects from each subgroup to meet a pre-determined quota.

Steps in Quota Sampling:

1. Identify the Population: Define the population you want to study.

2. Divide the Population into Subgroups: Based on specific characteristics (e.g., age, gender,
occupation).

3. Determine the Quotas: Decide how many subjects you need from each subgroup.

4. Select Subjects: Choose subjects from each subgroup non-randomly until the quota is met.

Example of Quota Sampling:

Suppose a researcher wants to study the shopping habits of a city's population. The researcher decides
to ensure that different age groups are represented in the sample. Here's how they might proceed:

1. Identify the Population: The entire population of the city.

2. Divide the Population into Subgroups: Age groups such as 18-29, 30-44, 45-59, and 60+.

3. Determine the Quotas: Based on the city's demographics, the researcher decides to have 100
respondents in total, with the following quotas:

o 18-29 years: 25 respondents

o 30-44 years: 25 respondents

o 45-59 years: 25 respondents

o 60+ years: 25 respondents

4. Select Subjects: The researcher goes to a shopping mall and interviews people who fit into these
age categories until they have reached the quota for each group.

Convenience sampling
is a non-probability sampling technique where subjects are selected based on their easy availability and
proximity to the researcher. This method is often used in exploratory research where the goal is to
obtain a quick and inexpensive sample.

Example of Convenience Sampling:

SAMPLING
Imagine you are conducting a study on the dietary habits of university students. You decide to use
convenience sampling due to time constraints.

1. Identify the Population: University students.

2. Select Subjects Based on Availability: You decide to survey students in the university cafeteria
during lunch hours.

Steps:

1. Go to a Location with Easy Access: You visit the university cafeteria.

2. Approach Available Students: You ask students who are having lunch if they are willing to
participate in your survey until you have reached your desired sample size

Purposive Sampling:

Purposive sampling (or judgmental sampling) involves selecting subjects based on specific
characteristics or criteria set by the researcher. This technique is used when the researcher wants to
focus on particular subgroups that are of interest to the study.

Example of Purposive Sampling: You are conducting a study on the dietary habits of vegetarians. You
specifically want to understand the dietary patterns of those who have been vegetarians for more than
five years.

1. Identify the Population: Vegetarians.

2. Set Criteria for Selection: Vegetarians who have been following the diet for more than five
years.

Steps:

1. Define the Criteria: Only include vegetarians who have adhered to the diet for over five years.

2. Select Subjects Based on Criteria: Reach out to vegetarian clubs, forums, or social media groups
and ask for volunteers who meet your criteria.

Definition of Snowball Sampling:

Snowball sampling is a non-probability sampling technique where existing study subjects recruit future
subjects from among their acquaintances. Thus, the sample group appears to grow like a rolling
snowball. This technique is particularly useful for studying populations that are hard to reach or identify
through other sampling methods.

Steps in Snowball Sampling:

1. Identify Initial Subjects: Start with a few individuals who are part of the target population.
SAMPLING
2. Recruit through Referrals: Ask these initial subjects to refer others who fit the study criteria.

3. Repeat the Process: Continue the referral process with the new subjects until the desired
sample size is reached.

Probability sampling technique

Simple Random Sampling:
Simple random sampling is a probability sampling technique where each member of a population has an
equal chance of being selected for the sample. This method ensures that the sample is unbiased and
representative of the entire population.

Methods of Simple Random Sampling:

1. Lottery Method:

o Write the names or numbers of all population members on separate pieces of paper.

o Mix the pieces of paper thoroughly.

o Draw the required number of pieces without looking to select the sample.

2. Random Number Tables:

o Assign a unique number to each member of the population.

o Use a random number table to select random numbers.

o The members corresponding to the selected numbers form the sample.

3. Computer-Generated Random Numbers:

o Assign a unique number to each member of the population.

o Use computer software or online tools to generate random numbers.

o The members corresponding to the generated numbers form the sample.

Systematic sampling
is a probability sampling technique where every kkk-th member of a population is selected for the
sample, starting with a randomly chosen point. This method ensures that the sample is spread evenly
across the population.

Steps in Systematic Sampling:

1. Define the Population: Determine the total number of units in the population ( NNN ).

2. Determine the Sample Size: Decide the number of units you want in your sample ( nnn ).
SAMPLING
3. Calculate the Sampling Interval ( kkk ): Divide the population size by the desired sample size
( k=Nnk = \frac{N}{n}k=nN ). This interval kkk is the number you will use to select every kkk-th
member.

4. Choose a Random Starting Point: Randomly select a starting point between 1 and kkk.

5. Select Every kkk-th Member: Starting from the randomly chosen point, select every kkk-th
member of the population.

 If the employees are listed in a roster from 1 to 1,000:

o Start at 7.

o Add the interval (10) to 7 to get the next selected employee (7 + 10 = 17).

o Continue adding the interval to the last selected number: 17 + 10 = 27, 27 + 10 = 37, and
so forth.

This method will produce a sample of employees: 7, 17, 27, 37, 47, 57, 67, 77, 87, 97, 107, ..., up to the
100th selected employee.

stratified sampling
is a probability sampling technique in which the population is divided into distinct subgroups or strata
that share similar characteristics. A random sample is then taken from each stratum, ensuring that each
subgroup is adequately represented in the overall sample. This method enhances the precision and
accuracy of the sample by accounting for differences between subgroups.

Steps in Stratified Sampling:

1. Define the Population: Identify the total population and the characteristic(s) by which it will be
stratified.

2. Divide the Population into Strata: Group the population into non-overlapping subgroups (strata)
based on the chosen characteristic(s).

3. Determine the Sample Size: Decide the total number of units you want in your sample ( nnn ).

4. Determine the Sample Size for Each Stratum: Decide how many units to sample from each
stratum, typically in proportion to the stratum's size relative to the entire population.

5. Randomly Select Samples from Each Stratum: Use simple random sampling or systematic
sampling within each stratum to select the sample units.

Example of Stratified Sampling:

Study on Student Academic Performance:

Imagine you are conducting a study on the academic performance of high school students, and you want
to ensure that students from different grade levels (9th, 10th, 11th, and 12th grades) are adequately
represented in your sample.

Steps:
SAMPLING
1. Define the Population: The population consists of all high school students in a particular school,
totaling 1,000 students.

2. Divide the Population into Strata: Group the students by grade level:

o 9th grade: 300 students

o 10th grade: 250 students

o 11th grade: 200 students

o 12th grade: 250 students

3. Determine the Sample Size: You want a total sample size of 200 students.

4. Determine the Sample Size for Each Stratum: Proportionally allocate the sample size to each
grade level:

o 9th grade: 3001000×200=60\frac{300}{1000} \times 200 = 601000300×200=60 students

o 10th grade: 2501000×200=50\frac{250}{1000} \times 200 = 501000250×200=50

students

o 11th grade: 2001000×200=40\frac{200}{1000} \times 200 = 401000200×200=40

students

o 12th grade: 2501000×200=50\frac{250}{1000} \times 200 = 501000250×200=50

students

5. Randomly Select Samples from Each Stratum: Use simple random sampling within each grade
level to select the required number of students.

Illustration:

 From the 9th grade (300 students), randomly select 60 students.

 From the 10th grade (250 students), randomly select 50 students.

 From the 11th grade (200 students), randomly select 40 students.

 From the 12th grade (250 students), randomly select 50 students.

By following these steps, you ensure that your sample of 200 students accurately represents the
distribution of students across the different grade levels, thereby providing a more precise and reliable
understanding of academic performance across the school

Cluster Sampling:

Cluster sampling is a probability sampling technique in which the population is divided into separate
groups, known as clusters. A random sample of clusters is then selected, and all members of the chosen
clusters are included in the sample. This method is often used when the population is large and widely
dispersed, making it impractical to conduct a simple random sample.
SAMPLING
Steps in Cluster Sampling:

1. Define the Population: Identify the entire population that you want to study.

2. Divide the Population into Clusters: Group the population into distinct clusters. These clusters
should ideally be as heterogeneous as possible internally but as homogeneous as possible
between each other.

3. Randomly Select Clusters: Use random sampling methods to select a predetermined number of
clusters from the population.

4. Collect Data from All Members of Selected Clusters: Survey or collect data from every individual
within the chosen clusters.

Example of Cluster Sampling:

Study on Community Health in a Large City:

Imagine you are conducting a study on community health in a large city with 100 neighborhoods. Each
neighborhood can be considered a cluster.

Steps:

1. Define the Population: The population consists of all residents in the city, spread across 100
neighborhoods.

2. Divide the Population into Clusters: Each neighborhood represents a cluster.

3. Determine the Number of Clusters to Sample: Suppose you decide to sample 10 neighborhoods
(clusters) out of the 100.

4. Randomly Select Clusters: Use a random number generator or draw lots to select 10
neighborhoods from the list of 100.

5. Collect Data from All Members of Selected Clusters: Visit each of the 10 selected
neighborhoods and collect health data from every resident in these neighborhoods.

Illustration:

1. List of Neighborhoods (Clusters):

o Neighborhood 1, Neighborhood 2, Neighborhood 3, ..., Neighborhood 100

2. Randomly Select 10 Neighborhoods:

o Suppose the randomly selected neighborhoods are Neighborhoods 4, 15, 22, 34, 45, 50,
63, 70, 85, and 90.

3. Survey All Residents in Selected Neighborhoods:

o Visit each of these 10 neighborhoods and collect health data from every resident in
these areas.
SAMPLING
By following these steps, you create a sample that represents the city's population without having to
survey every individual across all 100 neighborhoods, saving time and resources while still obtaining
valuable data.

Sampling Key
Definition Advantages Limitations When to Use
Technique Characteristics

Every When the

May require a
individual has population is small
Simple Random selection, Easy to complete list of
an equal or easily accessible,
Random equal probability understand and the population;
chance of and you can obtain
Sampling for all members. implement. not suitable for
being a complete list of all
large populations.
selected. members.

Select every When the

Uses a fixed Can introduce
kkk-th population is
interval to select Simpler and bias if there is a
individual ordered and you
Systematic every kkk-th quicker than pattern in the
from a list want an evenly
Sampling individual after simple random population that
after a distributed sample
random starting sampling. matches the
random across the
point. sampling interval.
starting point. population.

When the
Divide the
More precise More complex to population is
population
Ensures all estimates, implement and heterogeneous and
Stratified into subgroups
subgroups (strata) especially when requires you want to ensure
Sampling (strata) and
are represented. subgroups are knowledge of all relevant
sample from
distinct. strata. subgroups are
each stratum.
represented.

When the
Divide the
Cost-effective for May have higher population is large,
population
Randomly selects large, sampling error; dispersed, or
Cluster into clusters,
entire groups or geographically less precise if difficult to access,
Sampling then randomly
clusters. spread clusters are not and it is impractical
select whole
populations. homogenous. to list every
clusters.
individual.

When to Use Each Technique:

 Simple Random Sampling:

Best used when the population is small or accessible, and you have a complete list of all
members.
SAMPLING
 Systematic Sampling:
Ideal when you have a complete list of the population and the members are organized in some
way (e.g., a roster or directory).

 Stratified Sampling:
Perfect for populations with clear subgroups (e.g., age, gender, income groups) where you want
to ensure that each subgroup is represented proportionally in the sample.

 Cluster Sampling:
Most useful when the population is large, geographically spread out, or difficult to access. It’s
more practical and cost-effective when a full list of the population is not feasible, and you can
sample entire groups instead of individuals