Qualitative

sampling methods
Purposeful Sampling
• Researchers select participants based on specific criteria
related to their research objectives. This could include
maximum variation sampling (choosing diverse
participants) or typical case sampling (choosing the most
representative cases).
• **Research Objective**: A researcher is conducting a
qualitative study on the experiences of employees in a
multinational corporation who have participated in diversity
and inclusion training programs. The goal is to understand
how these training programs impact employees'
perceptions of workplace diversity and inclusion.
Example
In this case, purposeful sampling would involve selecting participants who meet specific criteria related to the
research objective. The researcher might choose:

1. **Diverse Group**: To capture a range of perspectives, the researcher selects participants from various
departments, levels of seniority, and cultural backgrounds within the company.

2. **Participants with Varying Training Experiences**: Some participants may have recently completed the
diversity training, while others may have done it in the past. This variation allows for insights into the long-term
impact of the training.

3. **Different Attitudes and Perceptions**: The researcher may purposefully select participants who hold
different attitudes toward diversity and inclusion, such as those who are enthusiastic about the training and
those who are skeptical.

4. **Gender and Age Diversity**: The researcher may also consider gender and age diversity to explore
potential differences in how different demographic groups perceive the training.

By purposefully selecting participants based on these criteria, the researcher ensures a diverse and
representative sample that can provide rich insights into the research question.
Snowball Sampling
• Used when it's challenging to identify participants
directly. The researcher starts with one or a few
participants and asks them to recommend others,
creating a "snowball" effect.
• **Research Objective**: A researcher is conducting a
qualitative study on the experiences of individuals who
have overcome addiction to opioids and successfully
reintegrated into society. The goal is to understand the
factors that contributed to their recovery and
reintegration.
Example
• **Snowball Sampling**: In this case, snowball sampling
would involve starting with one or a few initial
participants who meet the criteria (individuals in
recovery from opioid addiction). Then, the researcher
would ask these participants to recommend others who
have had similar experiences. This process continues
until the desired sample size is reached or until data
saturation is achieved.
1. **Initial Participant**: The researcher identifies and interviews an individual who has successfully
recovered from opioid addiction and reintegrated into society. This person becomes the first
participant in the study.

2. **Recommendations**: During the interview, the researcher asks the initial participant if they know
of others who have gone through a similar recovery journey. The initial participant might recommend
two or three other individuals.

3. **Contacting and Interviewing New Participants**: The researcher contacts and interviews the
individuals recommended by the initial participant. During these interviews, they ask the same
question about recommendations, and this process continues iteratively.

4. **Continued Snowballing**: As the interviews progress, each new participant is asked for
recommendations, and the process continues to identify more participants who fit the study's criteria.
This snowball sampling method is especially useful when it's challenging to identify and access
participants through traditional sampling methods, such as random sampling. It relies on social
networks and referrals to uncover hidden or hard-to-reach populations, like those in recovery from
addiction, and can lead to a diverse and interconnected sample for qualitative research.
Convenience Sampling
• Participants are chosen for their accessibility or
availability. While this method is less rigorous, it's often
used when time or resources are limited.
• **Research Objective**: A researcher is conducting a
study to explore the eating habits of university students
on a tight budget.
• **Convenience Sampling**: In this case, due to limited
time and resources, the researcher opts for convenience
sampling, which involves selecting participants based
on their accessibility and availability.
Examples
1. **Selection of Participants**: The researcher decides to collect data by surveying
students in the university's main cafeteria during lunchtime.

2. **Data Collection**: The researcher approaches students who are dining in the cafeteria
during the chosen time frame and asks them to participate in a brief survey about their
eating habits.

3. **Data Analysis**: The collected data is then analyzed to draw conclusions about the
eating habits of university students on a tight budget based on the responses of those who
were convenient to survey in the cafeteria during the researcher's available time.

Convenience sampling is often used in situations where the researcher's primary concern is
practicality and efficiency, and where it may be challenging to access a representative
sample due to constraints like time or budget. However, it's important to acknowledge that
the results of convenience sampling may not be generalizable to the entire population, as
the sample may not be truly representative.
Theoretical Sampling
• Common in grounded theory research, where participants are
selected based on emerging theories, allowing for the
development and refinement of theories as data is collected.
• **Research Objective**: A researcher is conducting a grounded
theory study to develop a theory about the coping strategies
used by parents of children with autism spectrum disorder
(ASD).

• **Theoretical Sampling**: In grounded theory research,

theoretical sampling is an iterative process where data collection
and analysis inform each other. The researcher starts with a
general research question but refines it as the study progresses.
Example
1. **Initial Data Collection**: The researcher begins by interviewing a few
parents of children with ASD about their coping strategies. These initial
interviews provide a preliminary understanding of the topic.

2. **Data Analysis**: After analyzing the initial interviews, the researcher

identifies emerging themes and concepts related to coping strategies. They
notice that parents often discuss seeking support from online communities.

3. **Refining the Research Question**: Based on this initial analysis, the

researcher decides to focus specifically on the role of online support
communities in coping. The research question becomes more specific, such
as "How do parents of children with ASD use online support communities to
cope with the challenges they face?"
4. **Sampling Continues**: The researcher then seeks out more participants who
have experience with online support communities and interviews them. As new
data is collected, the researcher continually refines the theory and adjusts the
sampling strategy to gather data that can further develop and validate the
emerging theory.

5. **Theoretical Saturation**: The process continues until theoretical saturation

is reached, meaning that no new information or themes are emerging, and the
theory is well-developed and supported by the data.

Theoretical sampling in grounded theory research allows the researcher to build

a theory that is grounded in the data itself, rather than relying on preconceived
notions or existing theories. It involves a flexible and adaptive approach to data
collection and analysis, ensuring that the theory evolves and deepens as the
study progresses.
Purposive Network Sampling
• Focuses on interconnected social networks, where
participants are chosen based on their position within the
network or their potential to provide valuable insights.
• **Research Objective**: A researcher is conducting a
qualitative study to explore the dynamics of information
sharing within a professional network of cybersecurity
experts.
• **Purposive Network Sampling**: In this case, the
researcher wants to select participants who are strategically
positioned within the network to provide valuable insights
Example
1. **Identifying Key Nodes**: The researcher begins by identifying key individuals within
the professional network who are known for their expertise in cybersecurity. These
individuals are considered "key nodes" because they have extensive knowledge and
connections within the network.

2. **Selecting Participants**: From the list of key nodes, the researcher purposively selects
a subset of individuals who represent different roles within the cybersecurity field, such as
threat analysts, penetration testers, and security architects.

3. **Interviewing Participants**: The selected participants are then interviewed about their
experiences, information-sharing practices, and network interactions within the
cybersecurity community.

4. **Additional Referrals**: During the interviews, participants may be asked to recommend

other experts or colleagues within the network who are actively engaged in information
sharing.
5. **Interviewing Recommended Participants**: The researcher interviews
the individuals recommended by the initial participants, further
expanding the sample and gaining a more comprehensive understanding
of the network dynamics.

6. **Data Analysis**: The data collected from these interviews are

analyzed to uncover patterns, relationships, and insights into how
information flows within the professional network and how key nodes
influence this process.

Purposive network sampling ensures that the study focuses on individuals

who play pivotal roles within a specific network, allowing for a deeper
exploration of the interactions and information-sharing practices within
that network. It helps in understan
Quota Sampling
• Researchers divide the population into subgroups and then
sample proportionally from each subgroup. This method
ensures representation from various segments of the
population.
• **Research Objective**: A researcher is conducting a study on
consumer preferences for a new type of organic cereal in a
large city. The goal is to ensure that the sample reflects the
demographic diversity of the city's population.
• **Quota Sampling**: In this case, the researcher aims to
select participants in a way that mirrors the population's key
demographic characteristics, such as age, gender, and
income, to ensure a representative sample.
Example
1. **Demographic Characteristics**: The researcher first identifies the relevant demographic
characteristics that are essential for achieving a representative sample. Let's say these
characteristics include age (young adults and middle-aged adults), gender (male and
female), and income level (low income and high income).

2. **Setting Quotas**: Quotas are set for each demographic category based on the known
distribution in the city. For example, if the city's population is 40% young adults and 60%
middle-aged adults, the researcher sets quotas accordingly.

3. **Sampling Process**: The researcher then collects data by approaching potential

participants in specific locations within the city. To fill the quotas, they may approach
individuals in shopping malls, parks, or other public places.

4. **Selection Criteria**: When recruiting participants, the researcher selects individuals who
fit into the designated demographic categories and quotas. For instance, if they've met the
quota for young adults, they will only approach middle-aged adults to fill the remaining slots.
5. **Data Collection**: Surveys or interviews are conducted with
participants to gather their preferences and opinions about the new
organic cereal.

6. **Adjusting Quotas**: If the researcher finds it challenging to fill a

particular quota, they continue their recruitment efforts in the targeted
demographic category until the desired number of participants is reached.

Quota sampling allows researchers to ensure that their sample reflects

the key demographic characteristics of interest in the population, even
though it's not based on random selection. It's a useful method when
random sampling is impractical or costly, as long as the quotas are well-
defined and accurately represent the population's composition.
Criterion Sampling
Participants are selected based on specific criteria or
characteristics that are crucial to the research. For
example, selecting individuals who have experienced a
particular event.
**Research Objective**: A researcher is conducting a study
on the experiences of individuals who have survived a
specific type of natural disaster, such as a hurricane.
**Criterion Sampling**: In this case, the researcher selects
participants based on specific criteria or characteristics
that are crucial to the research objective.
1. **Criteria Establishment**: The researcher defines specific criteria for
participation in the study, such as having directly experienced a Category
5 hurricane and survived it. This criterion is essential to ensure that the
participants have relevant experiences related to the research topic.

2. **Participant Selection**: The researcher identifies individuals who

meet the established criteria by reviewing disaster records, contacting
local authorities, or reaching out to disaster relief organizations. These
individuals are survivors of the specified hurricane.

3. **Informed Consent**: The selected survivors are contacted and

informed about the study's purpose, and their consent to participate is
obtained.
4. **Data Collection**: Interviews or surveys are conducted
with the survivors to collect in-depth information about their
experiences, coping strategies, and the challenges they
faced during and after the hurricane.

Criterion sampling is particularly valuable when the

researcher seeks to investigate a specific subset of the
population with unique experiences or characteristics
related to the research topic. It ensures that the participants
selected have the necessary qualifications or experiences to
provide insights directly relevant to the study's objectives.
Maximum Variation Sampling
Aims to capture diverse perspectives by deliberately selecting
participants with a wide range of characteristics or experiences.

**Research Objective**: A researcher is conducting a study on the

experiences of employees working in a large tech company. The
goal is to understand the impact of the company's remote work
policies on various employees' work-life balance.

**Maximum Variation Sampling**: In this case, the researcher aims

to capture diverse perspectives and experiences related to the
research topic by deliberately selecting participants with a wide
range of characteristics.
1. **Selection Criteria**: The researcher identifies key characteristics or variables that could
influence work-life balance, such as job role, length of employment, age, gender, and family
status.

2. **Variation in Characteristics**: To ensure maximum variation, the researcher intentionally

selects participants who represent different ends of the spectrum for each characteristic. For
example:
- Job Role: Selects employees from various roles, including software engineers, marketing
managers, and customer support representatives.
- Length of Employment: Includes both long-term employees with over 10 years of service and
recent hires with less than one year.
- Age: Represents a broad age range, from employees in their early 20s to those in their late
50s.
- Gender: Ensures a mix of male, female, and non-binary employees.
- Family Status: Includes participants who are single, married, with children, and without
children.
3. **Data Collection**: Interviews or surveys are conducted
with the selected participants to gather their insights and
experiences related to remote work policies and work-life
balance.

By employing maximum variation sampling, the researcher can

capture a wide array of perspectives and experiences within
the tech company, providing a comprehensive understanding
of how remote work policies affect employees with various
backgrounds, roles, and life situations. This approach helps
ensure that the research findings are rich and representative of
the diversity within the organization.
Sequential Sampling
Sampling continues until data saturation is reached, meaning that
new data no longer provide additional insights or information.

**Research Objective**: A researcher is conducting a qualitative

study on the experiences of patients who have been diagnosed
with a rare autoimmune disease. The goal is to gain a deep
understanding of their journey from diagnosis to treatment.

**Sequential Sampling**: In this case, the researcher employs

sequential sampling as an iterative process where data collection
continues until theoretical saturation is reached, meaning that no
new information or insights are emerging.
Example
1. **Initial Data Collection**: The researcher begins by conducting in-depth interviews
with the first few patients diagnosed with the autoimmune disease. These interviews
provide initial insights into their experiences, challenges, and coping strategies.

2. **Data Analysis**: After analyzing the initial interviews, the researcher identifies key
themes and concepts related to the patient experience. For example, they may find
themes related to the emotional impact of the diagnosis and the search for effective
treatments.

3. **Refinement of Research Questions**: Based on the analysis of the initial interviews,

the researcher may refine or expand their research questions to delve deeper into specific
aspects of the patient experience. For instance, they may want to explore the role of
support networks more comprehensively.

4. **Continued Data Collection**: The researcher then conducts additional interviews with
new patients, focusing on the refined research questions. These interviews provide more
in-depth information and allow the researcher to validate or refine emerging theories.
5. **Data Analysis and Saturation**: The process of collecting data,
analyzing it, refining research questions, and conducting more interviews
continues until theoretical saturation is achieved. Saturation occurs when
no new themes or insights are emerging from the data, indicating that a
comprehensive understanding of the patient experience has been
reached.

6. **Final Analysis and Theory Development**: With a saturated dataset,

the researcher conducts a final analysis to develop a grounded theory that
encapsulates the experiences of patients with the autoimmune disease.

Sequential sampling in this scenario allows the researcher to adapt and

refine the research focus based on emerging insights, ensuring that the
study's findings are comprehensive and grounded in the data itself.
Critical Case Sampling
Involves selecting cases that are expected to provide the most
significant insights or challenge existing theories.

**Research Objective**: A researcher is conducting a qualitative

study on the effectiveness of a new teaching method in a primary
school. The goal is to identify the factors that contribute to its
success or failure.

**Critical Case Sampling**: In this case, the researcher focuses on

selecting cases that are expected to provide the most significant
insights or challenge the existing assumptions about the teaching
method.
1. **Identification of Critical Cases**: The researcher identifies specific classes or
teachers within the school who are seen as critical cases. These could be:
- A class that has shown remarkable improvement in student performance since
implementing the new teaching method.
- A class that has experienced significant challenges or resistance to the new
teaching method.

2. **Data Collection**: The researcher conducts in-depth observations, interviews with

teachers, and surveys with students and parents in these critical cases. They gather
detailed information about the teaching method's implementation, challenges faced,
and outcomes achieved.

3. **Data Analysis**: The data collected from the critical cases are carefully analyzed to
identify key factors contributing to success or failure. This analysis can reveal insights
into why the method works well in some situations and not in others.
4. **Comparison with Non-Critical Cases**: To further enhance understanding, the
researcher may also collect data from non-critical cases (i.e., classes or teachers
who represent typical or average implementation of the teaching method) for
comparison. This helps highlight the unique aspects of the critical cases.

5. **Theory Development**: Based on the analysis of critical cases and

comparisons with non-critical cases, the researcher develops a theory or
framework that explains the conditions under which the teaching method is
effective and where it may need adjustments.

Critical case sampling is valuable when researchers want to explore extreme or

contrasting situations to gain insights that can inform theory development or policy
recommendations. By studying these critical cases, researchers can identify factors
critical to success or failure, helping to refine and improve teaching methods in this
example.
THANK YOU!