purposive sampling in qualitative research advantages

18 Advantages and Disadvantages of Purposive Sampling

Purposive sampling provides non-probability samples which receive selection based on the characteristics which are present within a specific population group and the overall study. It is a process that is sometimes referred to as selective, subjective, or judgmental sampling, but the actual structure involved remains the same.

There are several different purposive sampling types that researchers can use to collect their information.

• Heterogeneous or Maximum Variation • Homogenous • Typical Case Sampling • Deviant or Extreme • Critical Case Sampling • Expert • Total Population

Unlike the other sampling techniques that are useful under probability sampling, the goal of this work is to intentionally select subjects to gather information. Researchers are working with a specific goal in mind through the lens of quantitative research. The focus remains on individuals with specific characteristics in a targeted population group of interest.

Each type of sampling can be useful for situations when researchers must either target a sample quickly or for when proportionality is the primary concern. Although each type offers its own set of strengths and weaknesses to consider, they also come together to create a series of advantages and disadvantages for purposive sampling to review.

List of the Advantages of Purposive Sampling

1. You can take advantage of numerous qualitative research designs. Researchers are able to draw upon a wide range of qualitative research designs when their focus is on purposive sampling. Achieving the goals of these designs often requires a different type of sampling strategy and technique to gather the necessary data to draw a conclusion. The various techniques that are possible through the purposive approach allow research designs to be more adaptive, allowing for specific techniques to be applied when needed to work toward the end result.

2. There is still an opportunity to create generalizations from the data. Although you cannot extrapolate information from the targeted group to make generic claims about an entire population, the various purposive sampling techniques do provide researches with the justification to make a generalization from their sample. These efforts must be logical, analytic, or theoretical in nature to be valid. Each of the seven techniques takes a slightly different approach to this process, so it is up to the researchers involved with the project to determine how the work should proceed.

3. Purposive sampling can involve multiple phases. Not only can purposive sampling involve multiple phases for researchers, but it can also have each phase build upon the previous one. Even though this usually means a different type of technique is necessary at the start of each phase, this process is useful because it offers a wider range of non-probability sampling opportunities from which a researcher can draw. The classic example of this advantage is that critical sample can be useful in determining the value of an investigation, while the expert sampling approach allows for an in-depth analysis of the information that is present.

4. It helps by saving time and money while collecting data. The flexibility of purposive sampling allows researchers to save time and money while they are collecting data. It offers a process that is adaptive as circumstance change, even if it occurs in an unanticipated way. You can meet multiple needs and interests while still maintaining the foundation of a singular focal point. That is why it becomes possible to produce a final logical outcome that is representative of a specific population. You are taking a non-random approach to generate results that can then provide more information about future decisions that need to be made.

5. You can target niche demographics to obtain specific data points. When researchers use the homogeneous purposive sampling technique to collect information, then they are selecting individuals who have a shared set of characteristics. This similarity may involve emotional reactions, physical characteristics, or even household income levels. When researchers wanted to know how Caucasian people felt about the ideas of white privilege and racism, then they asked people who were white. You could follow the same processes for people who identify with a specific gender, work for the same employer, or any other shared characteristic that is important to study.

6. It is still possible to achieve a maximum level of variation in the purposive sample. By taking a heterogeneous approach to this research option, it is possible to select individuals from a diverse range of cases that are relevant to the issue being studied. The purpose of this design is to give researchers an opportunity to develop as much insight as they possibly can into whatever key point is under observation or examination. If you wanted to know how everyone in a community felt about a specific issue, then you would want to ask the same questions to as many different kinds of people as possible to create a strong perspective that represents the general public.

7. Purposive sampling allows researchers to look at the averages in the data. When the typical case sampling approach is taking using this process, then researchers are usually studying an event or trend that relates to who would be considered an “average” person in that specific demographic. It is even possible at times to pull information from past research opportunities to provide relevance to the updated data. If you want to know how a change in workplace procedures affects the average employee, then it would be necessary to contact the people who fit into a defined median from your demographic studies.

8. It can glean information from the various extremes of population groups. Purposive sampling can look at averages, but it will also help researchers to identify the extreme perspectives that are present in each population group as well. There are always outliers to consider in any project such as this, and their perspectives are just as critical at times as what the “median” person provides toward an outcome. This advantage makes it possible to have a better understanding about behavior patterns within a specific group, and it does not always need to be a negative perspective.

If researchers wanted to see why a specific group of students always achieved high grades while others did not, then they could purposely choose all of the individuals who reach the highest levels of success while ignoring everyone else.

9. You can select everyone in the population for the study with purposive sampling. There is no better way to understand how an entire population thinks or feels than to include every perspective in the data that you collect. This purposive technique makes it possible to prove the validity of the information immediately because no one is left out from the sampling process. Although this advantage takes more time because there is a significant amount of data to collect compared to the other types that are possible, researchers save time trying to “prove” their assertions because the material is useful in its raw form.

10. The information collected in purposive sampling has a low margin of error. When researchers approach a population group with a random survey, then the margin of error on their conclusions can be significant. Take a look at the political polls that news organizations announce regularly on their broadcasts. Most of them offer a margin of error that is between 3% to 6% – and sometimes even higher. If your results then say that individuals who say “yes” make up 48% of the population, but the people who say “no” are 52% of it, the margin of error can negate whatever result you hoped to achieve.

Researchers achieve a lower margin of error using the purposive sampling approach because the information they collect comes straight from the source. Each person has identifiable characteristics that place them into the same demographic. You’re not polling a random sample. You are working people who think or act the same way in specific situations.

11. Purposive sampling can produce results that are available in real-time. When researchers use surveys or polls to collect data from a specific population sample, then the information they acquire is useful in real-time situations. The members of the sample group all possess an appropriate level of understanding and knowledge about the subject being evaluated, which means there is less downtime involved. You do not need to process the data to glean results because it is possible to ask targeted questions that produce the exact answers that you require in each situation.

List of the Disadvantages of Purposive Sampling

1. It provides a significant number of inferential statistical procedures that are invalid. When you use purposive sampling for information collection, then you will discover that there is a vast array of inferential statistical procedures that are present in this structure. These statistics become invalid. They allow you to generalize from specific samples to a larger population group, making statements about the validity or accuracy of your discoveries. Because the data is more complex than what you would receive from a random sample, the only inference possibilities apply to the specific group that you are studying.

2. This process is extremely prone to researcher bias. Purposive sampling is highly prone to researcher bias no matter what type of method is being used to collect data. The idea that a sample is created in the first place relies on the judgment of the researcher, as well as their personal interpretation of the data. When the judgments are either poorly considered or ill-conceived, then this problem becomes a significant disadvantage that can provide roadblocks in the way of a final result. When there is elicitation, accepted criteria, or a theoretical framework in place, then this issue is minimized.

3. It may be challenging to defend the representative nature of a sample. Researchers must provide evidence that the judgment used to select the various units or individuals in the purposive sampling was appropriate for the processed used. The high levels of subjectivity cast an inevitable shadow of doubt on the results in almost every situation. Unless there is a way to defend the overall representative structures that were implemented to generate results, there will always be readers who feel unsure about the generalizations achieved, even when the theoretical, logical, or analytical structures are present.

4. The participants in purposive sampling can also manipulate the data being collected. When people know that they’ve been selected for a research project, then it can initiate a change in their behavior. They might choose to act in a way that allows researchers to reach the conclusions that they expect to see, or the opposite issue can occur as well. Some participants may choose to lie to create an unwanted outcome because they have a bias of their own that they want to take public. Only the skill of the researchers can determine if there is validity in the data collected, which means there are times when the outcome being studied could be more unpredictable than anticipated.

5. It can be an ineffective method when applied to large population groups. Although total population sampling is one of the purposive methods that researchers can use when collecting data, this process is at its most effective when there are a limited number of individuals or units who possess the specific traits that are being studied. Trying to initiate a random sample to serve as a foundation for theoretical supposition would be virtually impossible. You must go to the people with the specific traits that you wish to analyze for this research method to be useful. If that is not possible, then purposive sampling will not provide results at all.

6. There is no way to evaluate the reliability of the expert or authority in purposive sampling. There are occasional exceptions to this particular disadvantage, but there is usually no way to evaluate the reliability of the authority involved or the experts who are performing the purposive sampling. That means it can be virtually impossible to determine if there is a sampling error that is present in the information that researchers present. Even when the most experienced individuals in the industry under study are presenting the information, there is room to question the interpretation of the results. That is why there are times when purposive sampling is the weakest option to choose.

7. Purposive sampling can still produce inaccurate assumptions. When evaluating the overall sampling process, there is no randomization involved in purposive sampling because that would negate its purpose in the first place. It would not benefit researchers to speak with 40-year veterans of the workforce when they want to collect information about twenty-something entrepreneurs navigating the gig economy. There will always be a bias in this information. Because the members of the population being studied do not always have equal chances of selection, then even the logical process of sampling may generate inaccurate results.

The margin of error is smaller with this process than it would be with a randomized process, but it still exists. It may also be larger than a random sample if researchers use a large enough sample for their data collection needs.

One Final Consideration on the Advantages and Disadvantages of Purposive Sampling

Purposive sampling relies on the presence of relevant individuals within a population group to provide useful data. If researchers cannot find enough people or units that meet their criteria, then this process will become a waste of time and resources. The goal of this work is to find a range of cases that meet predetermined definitions to offer more insight into specific ideas, concerns, or issues within specific population groups.

Because the researchers are in charge of the selection process, their perspectives can influence the data they collect in numerous ways. Even when there is a conscious effort to set aside a bias, some may unconsciously manipulate the data that is available to create outcomes that support their preconceived notions.

The advantages and disadvantages of purposive sampling offer significant levels of flexibility, but they also require a higher level of evidence-based techniques to prove to outside observers that there is relevance to the information collected. That is why this process is usually reserved for situations where there is already a general consensus in the public about the definitions of certain population groups.

• What is purposive sampling?

Last updated

5 February 2023

Reviewed by

Cathy Heath

This type of sampling is often used in qualitative research , allowing the researcher to focus on specific areas of interest and gather in-depth data on those topics. In this article, we will explore the concept of purposive sampling in more detail and discuss the advantages and limitations of using this approach in research studies.

Analyze all your qualitative research

Analyze qualitative data faster and surface more actionable insights

Purposive sampling is a technique used in qualitative research to select a specific group of individuals or units for analysis. Participants are chosen “on purpose,” not randomly. It is also known as judgmental sampling or selective sampling.

In purposive sampling, the researcher has a specific purpose or objective in mind when selecting the sample. Therefore, the sample is selected based on the characteristics or attributes that the researcher is interested in studying. 

For example, suppose a researcher is interested in studying the experiences of individuals living with chronic pain. In that case, they might use purposive sampling to select a sample of individuals who have been diagnosed with chronic pain.

Purposive sampling is often used in qualitative research , as it allows the researcher to focus on specific areas of interest and gather in-depth data on those topics. It is also commonly used in small-scale studies with limited sample size.

• When to use purposive sampling

Purposive sampling should be used when you have a clear idea of the specific attributes you're interested in studying and want to select a sample that accurately represents those characteristics.

Purposive sampling can be particularly useful in the following situations:

When the population of interest is small

For interest in studying a specific subgroup within the population

To study a rare or unusual phenomenon

It's important to note that purposive sampling is not suitable for all research studies and should be used cautiously. As the sample is not selected randomly, the results of the study may not be generalizable to the larger population, and the researcher must consider the potential for bias in the sample selection.

• Principles of purposeful sampling

There are several important principles of purposive sampling that you should consider when using this approach in your research studies:

Clearly defined purpose - The purpose of the study should be clearly defined, and the sample should be selected based on the characteristics or attributes that you're interested in studying.

Representative sample - The sample should be representative of the characteristics or attributes being studied.

Bias - Biases can come into play when anything other than random sampling is used, so be aware of any potential biases and take steps to minimize them.

Expertise - Having expertise in the topic being studied is an important part of sample selection. Without a solid understanding of the characteristics being selected, the population might not be as representative as it should be.

• How is purposive sampling conducted?

The steps to conducting a study using purposive sampling will vary depending on the topic and preferences of the researchers involved. The five steps of purposive sampling as a general framework are:

Define the purpose of the study

Identify the sample of individuals or units

Obtain informed consent from individuals

Collect the data using appropriate research methods

Analyze the data

• Purposive sampling examples

Researchers can use several different types of purposive sampling methods , depending on what they're interested in studying and the specific research question they are trying to answer. In the list below, we'll discuss the various types of purposive sampling methods and provide examples of when each method might be used in research.

Maximum variation sampling

Maximum variation sampling involves selecting a sample of individuals or units representing the maximum range of variation within the characteristics or attributes the researcher is interested in studying. This type of sampling is used to understand the widest possible diversity of experiences or viewpoints within the population.

Homogeneous sampling

Homogeneous sampling involves selecting what is often a more narrow sample of individuals or units that are similar or have the same characteristics or attributes. This type of sampling is used to study a specific subgroup within the population in depth.

Typical case sampling

Typical case sampling involves selecting a sample of individuals or units that are representative of the typical experiences or characteristics of the population. This type of sampling is used to understand the most common or average experiences or characteristics within the population.

Extreme/deviant case sampling

Extreme case sampling involves selecting a sample of individuals or units that are considered extreme or unusual in the characteristics or attributes the researcher is interested in studying. This type of sampling is used to understand unusual or exceptional experiences or characteristics within the population and are often viewed as outliers in a wider population.

Critical case sampling

Critical case sampling involves selecting a sample of individuals or units that are important or central to the research question or the population being studied. This type of sampling is used to understand key experiences or characteristics within the population.

Expert sampling

Expert sampling involves selecting a sample of individuals or units that have specialized knowledge or expertise in the topic or issue being studied. This type of sampling is used to gather insights and understanding from experts in the field, which can be used to develop follow-up studies.

• Purposive sampling vs. convenience sampling

Purposive sampling and convenience sampling are similar in that both involve the selection of a sample based on the researcher's judgment rather than using a random sampling method. However, there are some key differences between the two approaches.

In purposive sampling, the sample is selected based on the defined purpose of the study and is intended to be representative of the characteristics or attributes in which the researcher is interested.

Convenience sampling, on the other hand, involves selecting a sample of individuals or units that are readily available or easily accessible to the researcher. The sample is not selected based on any particular characteristics or attributes, but rather in terms of convenience for the researcher.

• Advantages of purposive sampling

There are several advantages to using purposive sampling in research studies, including:

Representative sample - allows the researcher to select a sample highly representative of the characteristics or attributes they are interested in studying, relatively quickly, This can be particularly useful when the population of interest is small or when the researcher is interested in studying a specific subgroup within the population.

In-depth data - often used in qualitative research, which allows the researcher to gather in-depth data on specific topics or issues. This can provide valuable insights and understanding of the research question.

Practicality - practical and efficient in comparison to other sampling methods, particularly in small-scale studies with limited sample sizes.

Flexibility - flexibility in the selection of the sample, which can be useful when the researcher is studying a rare or unusual phenomenon.

Cost - can be less expensive than other sampling methods, as it does not require a random selection process.

• Disadvantages of purposive sampling

It's important to note that purposive sampling has limitations and should be used with caution. Some of the disadvantages of purposive sampling are listed below:

Limited generalizability -  As the sample is not selected randomly, the study’s results may not be generalizable to the larger population. Other risk factors are producing lop-sided research, where some subgroups are omitted or excluded.

Bias - Purposive sampling is subjective and relies on the researcher's judgment, which can introduce bias into the study. The researcher may unconsciously select individuals or units that fit their expectations or preconceived notions, which can affect the study’s validity. Participants can also manipulate the insights they give.

Sampling error - Sampling error, or the difference between the sample and the population, is more likely to occur in purposive sampling because the sample is not selected randomly. This can affect the reliability and accuracy of the study.

Limited sample size - Purposive sampling is often used in small-scale studies with limited sample sizes. This can affect the statistical power of the study and make it more difficult to detect significant differences or relationships.

Ethical considerations -  The researcher must ensure that the study is conducted ethically and that the rights of the participants are protected. This may require obtaining informed consent from the individuals in the sample and safeguarding their privacy.

• Challenges to the use of purposeful sampling

One of the main challenges to the use of purposive sampling in research studies is the limited generalizability of the findings. Because the sample is not selected randomly, it may not be representative of the broader population, and study results may not be applicable to other groups or populations. This can limit the usefulness and impact of the study, making it more challenging to draw conclusions about the larger population.

Each of the disadvantages listed in the previous section contributes to this problem. Researchers who wish to use purposive sampling need to be aware of the method’s weaknesses and actively take steps to avoid or mitigate them.

Why is purposive sampling used?

Purposive sampling is used in research studies when the researcher has a clear idea of the characteristics or attributes they are interested in studying and wants to select a sample that is representative of those characteristics. It is often used in qualitative research to gather in-depth data on specific topics or issues.

What is an example of purposive sampling?

An example of purposive sampling might be a researcher studying the experiences of individuals living with chronic pain, and therefore selecting a sample of individuals who have been diagnosed with chronic pain.

What type of research uses purposive sampling?

Purposive sampling is often used in qualitative research, as it allows the researcher to gather in-depth data on specific topics or issues. It may also be used in small-scale studies with a limited sample size.

What is a good sample size for purposive sampling?

The sample size for purposive sampling will depend on the research question and the characteristics or attributes the researcher is interested in studying. Generally, a sample size of 30 individuals is often considered sufficient for qualitative research, although larger sample sizes of 100 or more may be needed in some cases.

Get started today

Go from raw data to valuable insights with a flexible research platform

Editor’s picks

Last updated: 21 December 2023

Last updated: 16 December 2023

Last updated: 6 October 2023

Last updated: 25 November 2023

Last updated: 12 May 2023

Last updated: 15 February 2024

Last updated: 11 March 2024

Last updated: 12 December 2023

Last updated: 18 May 2023

Last updated: 6 March 2024

Last updated: 10 April 2023

Last updated: 20 December 2023

Latest articles

Related topics, log in or sign up.

Get started for free

• Privacy Policy

Home » Purposive Sampling – Methods, Types and Examples

Purposive Sampling – Methods, Types and Examples

Table of Contents

Purposive Sampling

Definition:

Purposive sampling is a non-probability sampling technique used in research to select individuals or groups of individuals that meet specific criteria relevant to the research question or objective.

This sampling technique is also known as judgmental sampling or selective sampling, and it is often used when the population being studied is too small, too difficult to access, or too heterogeneous to use probability sampling methods.

Purposive Sampling Methods

Purposive Sampling Methods are as follows:

• Expert sampling: In expert sampling, the researcher selects participants who are experts in a particular field or subject matter. This can be useful when studying a specialized or technical topic, as experts are likely to have a deeper understanding of the subject matter and can provide valuable insights.
• Maximum variation sampling: Maximum variation sampling involves selecting participants who represent a wide range of characteristics or perspectives. This can be useful when the researcher wants to capture a diverse range of experiences or viewpoints.
• Homogeneous sampling : In homogeneous sampling, the researcher selects participants who have similar characteristics or experiences. This can be useful when studying a specific subpopulation that shares common traits or experiences.
• Critical case sampling : Critical case sampling involves selecting participants who are likely to provide important or unique insights into the research question. This can be useful when the researcher wants to focus on cases that are particularly relevant or informative.
• Snowball sampling : Snowball sampling involves selecting participants based on referrals from other participants in the study. This can be useful when studying hard-to-reach or hidden populations, as it allows the researcher to gain access to individuals who may not be easily identifiable or accessible.

How to Conduct Purposive Sampling

Here are the general steps involved in conducting purposive sampling:

• Identify the research question or objective: The first step in conducting purposive sampling is to clearly define the research question or objective. This will help you determine the criteria for participant selection.
• Determine the criteria for participant selection : Based on the research question or objective, determine the specific criteria for selecting participants. These criteria should be relevant to the research question and should help you identify individuals who are most likely to provide valuable insights.
• Identify potential participants: Once you have determined the criteria for participant selection, identify potential participants who meet these criteria. Depending on the sampling method you are using, this may involve reaching out to experts in the field, identifying individuals who share certain characteristics or experiences, or asking for referrals from existing participants.
• Select participants: Based on the identified potential participants, select the individuals who will participate in the study. Make sure to select a sufficient number of participants to ensure that you have a representative sample.
• Collect data: After selecting participants, collect data using the appropriate research methods. Depending on the research question and objectives, this may involve conducting interviews, administering surveys, or collecting observational data.
• Analyze data: After collecting data, analyze it to answer the research question or objective. This may involve using statistical analysis, qualitative analysis, or a combination of both.

Examples of Purposive Sampling

Here are some examples of how purposive sampling might be used in research:

• Studying the experiences of cancer survivors : A researcher might use maximum variation sampling to select a diverse group of cancer survivors, with the aim of capturing a range of experiences and perspectives on the impact of cancer on their lives.
• Exploring the perspectives of teachers on a new curriculum : A researcher might use expert sampling to select teachers who are experts in a particular subject area or who have experience teaching the new curriculum. These teachers can provide valuable insights on the strengths and weaknesses of the new curriculum.
• Investigating the impact of a new therapy on a specific population: A researcher might use homogeneous sampling to select participants who share certain characteristics, such as a particular diagnosis or age group. This can help the researcher assess the effectiveness of the new therapy on this specific population.
• Examining the experiences of refugees resettling in a new country : A researcher might use critical case sampling to select participants who have experienced particularly challenging resettlement experiences, such as those who have experienced discrimination or faced significant barriers to accessing services.
• Understanding the experiences of homeless individuals : A researcher might use snowball sampling to identify and select homeless individuals to participate in the study. This method allows the researcher to gain access to a hard-to-reach population and capture a range of experiences and perspectives on homelessness.

Applications of Purposive Sampling

Purposive sampling has a wide range of applications across different fields of research. Here are some examples of how purposive sampling can be used:

• Medical research: Purposive sampling is commonly used in medical research to study the experiences of patients with specific medical conditions. Researchers might use homogeneous sampling to select patients who share specific medical characteristics, such as a particular diagnosis or treatment history.
• Market research: In market research, purposive sampling can be used to select participants who represent a particular demographic or consumer group. This might involve using quota sampling to select participants based on age, gender, income, or other relevant criteria.
• Education research: Purposive sampling can be used in education research to select participants who have specific educational experiences or backgrounds. For example, researchers might use maximum variation sampling to select a diverse group of students who have experienced different teaching styles or classroom environments.
• Social science research : In social science research, purposive sampling can be used to select participants who have specific social or cultural backgrounds. Researchers might use snowball sampling to identify and select participants from hard-to-reach or marginalized populations.
• Business research: In business research, purposive sampling can be used to select participants who have specific job titles, work in particular industries, or have experience with specific products or services

Purpose of Purposive Sampling

The purpose of purposive sampling is to select participants based on specific criteria relevant to the research question or objectives. Unlike probability sampling techniques, which rely on random selection to ensure representativeness, purposive sampling allows researchers to select participants who are most relevant to their research question or objectives.

Purposive sampling is often used when the population of interest is rare, hard to reach, or has specific characteristics that are important to the research question. By selecting participants who meet specific criteria, researchers can gather valuable insights that can help inform their research.

The ultimate goal of purposive sampling is to increase the validity and reliability of research findings by selecting participants who are most relevant to the research question or objectives. This can help researchers to make more accurate inferences about the population of interest and to develop more effective interventions or solutions based on their findings.

When to use Purposive Sampling

Purposive sampling is appropriate when researchers need to select participants who meet specific criteria relevant to their research question or objectives. Here are some situations where purposive sampling might be appropriate:

• Rare populations: Purposive sampling is often used when the population of interest is rare, such as people with a particular medical condition or individuals who have experienced a particular event or phenomenon.
• Hard-to-reach populations: Purposive sampling is also useful when the population of interest is hard to reach, such as homeless individuals or individuals who have experienced trauma or abuse.
• Specific characteristics: Purposive sampling is appropriate when researchers need to select participants with specific characteristics that are relevant to the research question, such as age, gender, or ethnicity.
• Expertise : Purposive sampling is useful when researchers need to select participants with particular expertise or knowledge, such as teachers or healthcare professionals.
• Maximum variation : Purposive sampling can be used to select participants who represent a range of perspectives or experiences, such as individuals from different socio-economic backgrounds or who have different levels of education.

Characteristics of Purposive Sampling

Purposive sampling has several characteristics that distinguish it from other sampling methods:

• Non-random selection : Purposive sampling involves the deliberate selection of participants based on specific criteria, rather than random selection. This allows researchers to select participants who are most relevant to their research question or objectives.
• Small sample sizes: Purposive sampling typically involves smaller sample sizes than probability sampling methods, as the focus is on selecting participants who meet specific criteria, rather than ensuring representativeness of the larger population.
• Heterogeneous or homogeneous samples : Purposive sampling can involve selecting participants who are either similar to each other (homogeneous) or who are diverse and represent a range of perspectives or experiences (heterogeneous).
• Multiple sampling strategies: Purposive sampling involves a range of sampling strategies that can be used to select participants, including maximum variation sampling, expert sampling, quota sampling, and snowball sampling.
• Flexibility : Purposive sampling is a flexible method that can be adapted to suit different research questions and objectives. It allows researchers to select participants based on specific criteria, making it a useful method for exploring complex phenomena or researching hard-to-reach populations.

Advantages of Purposive Sampling

Purposive sampling has several advantages over other sampling methods:

• Relevant participants: Purposive sampling allows researchers to select participants who are most relevant to their research question or objectives, ensuring that the data collected is of high quality and useful for the research.
• Efficient : Purposive sampling is an efficient method of sampling, as it allows researchers to select participants based on specific criteria, rather than randomly selecting a large number of participants. This can save time and resources, especially when the population of interest is rare or hard to reach.
• Representative : Purposive sampling can produce samples that are representative of the population of interest, as researchers can use a range of sampling strategies to select participants who are diverse and represent a range of perspectives or experiences.
• Ethical considerations : Purposive sampling can be used to ensure that vulnerable or marginalized populations are included in research studies, ensuring that their voices and experiences are heard and taken into account.

Disadvantages of Purposive Sampling

Some Disadvantages of Purposive Sampling are as follows:

• Sampling bias: Purposive sampling is susceptible to sampling bias, as the participants are not randomly selected from the population. This means that the sample may not be representative of the larger population, and the findings may not be generalizable to other populations.
• Limited generalizability: The findings obtained from purposive sampling may be limited in their generalizability due to the small sample size and the specific selection criteria used. Therefore, it may not be possible to make broad generalizations based on the findings of a purposive sample.
• Lack of transparency : The selection criteria used in purposive sampling may not be transparent, and this can limit the ability of other researchers to replicate the study.
• Reliance on researcher judgment : Purposive sampling relies on the researcher’s judgment to select participants based on specific criteria, which can introduce bias into the selection process.
• Potential for researcher subjectivity : The researcher’s subjectivity and bias may influence the selection process and the interpretation of the data collected.

About the author

Muhammad Hassan

Researcher, Academic Writer, Web developer

You may also like

Probability Sampling – Methods, Types and...

Quota Sampling – Types, Methods and Examples

Sampling Methods – Types, Techniques and Examples

Simple Random Sampling – Types, Method and...

Convenience Sampling – Method, Types and Examples

Systematic Sampling – Types, Method and Examples

Purposive Sampling in Qualitative Research

Introduction

What is the purposive sampling method, what is purposive sampling used to identify, when to use purposive sampling, types of sampling methods, advantages of purposive sampling, disadvantages of purposive sampling, how to conduct purposive sampling.

In qualitative research studies that involve methods such as interviews , focus groups , and surveys , purposive sampling is useful when the researcher wants to collect qualitative data from a specific population with particular characteristics.

Purposive sampling or judgmental sampling stands in contrast to random sampling or probability sampling, which aims to collect data randomly to ensure the generalization of findings across an entire population. Instead, the objective in purposive sampling is to target a specific subset of people to more deeply understand the unique or diverse variations in a culture or context.

In this article, we'll examine the different kinds of purposive sampling and the considerations involved with conducting research through purposive sampling.

Purposive sampling, also known as judgmental or selective sampling, is a non-probabilistic sampling technique used extensively in qualitative research . This method involves deliberately choosing participants based on the characteristics of a population and the objectives of the study. Unlike random probability sampling , where every member of the population has an equal chance of being selected, purposive sampling allows researchers to use their judgment to select cases that will best contribute to the data collection and the objectives of the research.

The essence of purposive sampling lies in selecting information-rich cases. These can be individuals, groups, or occurrences that are relevant to the issue being studied. For example, if a study aims to understand the experiences of cancer survivors, purposive sampling would involve selecting individuals who have lived through cancer, as they can provide depth and insight into the research question .

This method is widely preferred in exploratory studies, where detailed understanding rather than generalization is the goal. It enables researchers to focus on specific characteristics, conditions, or phenomena that are central to the research question. The idea is not to randomly select cases in a way that mirrors the population, but rather to select cases that will illuminate the topic of interest more richly and in depth.

Ultimately, purposive sampling is a strategic choice by researchers to select participants who can provide the most informative data, rather than aiming for a broad representation of the entire population. This approach is crucial when the researcher aims to explore specific themes, patterns, or phenomena within a subset of a population, which requires detailed and nuanced insights.

Purposive sampling is primarily used to identify specific characteristics, trends, or insights within a targeted subset of a population. This method is particularly effective in identifying unique or exceptional cases that are not readily observable in the broader population. By focusing on particular characteristics or experiences, purposive sampling allows researchers to delve into the depth and complexity of the subject matter, providing rich, detailed insights.

The key objective of purposive sampling is to gain a deep understanding of phenomena from a specific perspective or within a specific context. For instance, in a study about educational practices, researchers might use purposive sampling to select teachers who are implementing innovative teaching methods. Here, the focus is not on how common these practices are, but on understanding the nature, challenges, and impacts of these innovations in depth.

Furthermore, purposive sampling is instrumental in identifying and exploring patterns or themes that emerge within a particular group. This can include exploring the experiences of a minority group, understanding behaviors in a specific cultural setting, or examining the impacts of a policy on a targeted demographic. The method ensures that the sample provides the necessary information to answer the research questions, even if it does not statistically represent the larger population.

In essence, purposive sampling is used to extract meaningful and in-depth information from a selected group of participants, providing qualitative insights that are often unattainable through more generalized sampling methods.

Purposive sampling is most appropriate in qualitative research when the aim is to gain detailed and nuanced understanding of specific phenomena, rather than to generalize findings to a larger population. This approach is particularly useful in several scenarios:

Exploratory research

When little is known about a phenomenon and the goal is to develop propositions or theories, purposive sampling helps in selecting cases rich in information. It is ideal for initial explorations where specific insights are needed to form a basis for further study.

Studying unique or specific cases

In cases where the research focuses on specific types of individuals, events, or phenomena, purposive sampling allows researchers to deliberately target these instances. For example, studying the experiences of a particular professional group or examining rare events can be realized through purposive sampling.

Context-dependent knowledge

When the research question requires deep understanding of the context or the environment, purposive sampling enables the selection of participants who have experienced or are immersed in that context.

Resource constraints

In situations where resources, such as time and money, are limited, purposive sampling offers a practical approach to focus on key informants or critical cases that provide the most valuable data.

Theory or concept testing

When testing theories or concepts, purposive sampling can be used to select cases that are most likely to challenge or support these theories.

Turn to ATLAS.ti for all your research needs

Download a free trial to see how you can make the most of your qualitative data.

Purposive sampling encompasses various methods, each tailored to specific research objectives and contexts. These methods allow researchers to strategically select participants based on particular criteria, ensuring the collected data is most relevant to the study.

Below is an overview of the different types of purposive sampling methods. Each of these purposive sampling methods offers unique advantages and is suited to specific research scenarios, enabling researchers to gather rich, targeted data for their qualitative studies .

Convenience sampling

This method involves selecting participants who are easily accessible to the researcher. It's often used for preliminary or exploratory studies where convenience and speed are prioritized over representativeness.

Snowball sampling

Snowball sampling is used when potential participants are hard to locate. Researchers start with a few known subjects who then refer others, creating a 'snowball' effect in participant recruitment.

Cluster sampling

In cluster sampling , the population is divided into clusters, and then a few clusters are chosen at random for research. This method is beneficial when studying a large population dispersed over a wide area.

Heterogeneous sampling

Also known as maximum variation sampling, this approach focuses on capturing a wide range of perspectives by selecting participants with varied characteristics. It's ideal for exploring the breadth of a phenomenon.

Homogeneous sampling

In contrast to heterogeneous sampling, this method selects participants with similar characteristics or experiences, facilitating an in-depth study of a particular subgroup.

Typical case sampling

Researchers select 'typical' cases that are average or representative of the population. This method is useful for providing an illustrative snapshot of the norm.

Critical case sampling

This method involves selecting cases that are crucial for the research question , often because they can make or break a theory or hypothesis .

Extreme case sampling

This approach focuses on unusual or rare cases that are different from the norm, providing insights into atypical phenomena.

Stratified sampling

Stratified sampling involves dividing the population into subgroups and selecting samples from each subgroup. This can ensure representation across key characteristics or variables.

Purposive sampling offers several significant advantages in qualitative research , particularly when the focus is on gaining deep, contextualized insights rather than generalizable data. Let's look at some of the key advantages.

Purposive sampling allows for the selection of participants who are most relevant to the research question. This targeted approach ensures that the data collected is rich and directly pertinent to the study's objectives, leading to more meaningful and focused findings.

Since this method often involves selecting participants with specific experiences or knowledge, it facilitates the collection of in-depth information. Researchers can delve into complex topics with participants who offer detailed insights, making it possible to explore nuances and subtleties that might be missed with a more generalized approach.

Purposive sampling is highly adaptable to the needs of a study. Researchers can adjust their sampling strategy as they learn more about their subject, allowing for a responsive and evolving research process. This flexibility is particularly valuable in exploratory studies or when new themes emerge during the research.

By focusing on specific individuals or groups, purposive sampling can be more time and resource-efficient compared to probability sampling methods. It reduces the need for a large sample size while still providing rich, valuable data.

This method is especially advantageous when studying hard-to-reach, specialized, or vulnerable populations. Purposive sampling allows researchers to carefully select participants who can provide insights into these unique groups, which might be difficult to achieve with random sampling .

Finally, purposive sampling is conducive to theory development. By selecting cases that are particularly informative for understanding the research question , this method can significantly contribute to theoretical insights and advancements.

While purposive sampling is highly beneficial for certain qualitative research studies, it also has several disadvantages that researchers must consider.

The most significant drawback of purposive sampling is the limited ability to generalize findings to the broader population. Since samples are specifically selected based on certain criteria or characteristics, they may not adequately represent the diversity and variability present in the larger population.

This method relies heavily on the researcher's judgment in selecting participants. This inherent subjectivity can introduce bias , as the researcher's perspectives and preconceptions may influence the choice of sample, potentially leading to skewed or one-sided data.

The subjective nature of sample selection in purposive sampling also makes it challenging to replicate studies. Different researchers might choose different participants, which can result in varying findings and conclusions, potentially limiting the reliability of the research.

In purposive sampling, there is a risk of overemphasizing particular viewpoints, especially those of more vocal or articulate participants, while underrepresenting less prominent perspectives. This can skew the research outcomes and reduce the depth of understanding.

Finally, the non-random selection process increases the risk of sampling errors. The sample might not adequately capture the complexity or nuances of the broader population, leading to partial or incomplete findings.

Conducting purposive sampling in qualitative research demands a structured and thoughtful approach that closely aligns with the study's objectives. The process begins with a clear articulation of these objectives and the establishment of criteria for participant selection. This crucial first step involves identifying specific characteristics, experiences, or knowledge that the participants need to possess to provide relevant insights into the research question .

Once the research goals and criteria are defined, the next task is to identify the broader population relevant to the study. From this larger group, participants who meet the established criteria are selected. The selection of the appropriate purposive sampling method is a critical decision that should be based on the specific aims of the research. Various methods , such as homogeneous sampling for in-depth exploration of a specific group or critical case sampling for testing a theory, can be chosen depending on what aligns best with the study's goals.

The recruitment of participants is a dynamic process. It may involve directly reaching out to specific individuals, employing snowball techniques to find suitable participants, or collaborating with organizations or communities. While focusing on specific criteria, it's important to ensure a diverse range of participants within those parameters to provide a comprehensive understanding of the topic.

Throughout the sampling process, continually evaluating the adequacy of the sample size and composition is essential. The focus should be on the richness of the data , which often dictates the adequacy of the sample size, rather than merely the number of participants.

Lastly, documenting every decision and rationale throughout the process is vital for the credibility of the research. This transparency allows others to understand the hows and whys of participant selection, reinforcing the integrity of the study.

By meticulously following these guidelines, researchers can effectively implement purposive sampling, ensuring that their sample provides rich, targeted data that is in line with the study's objectives.

Turn data into critical insights with ATLAS.ti

Use our intuitive data analysis interface to further your qualitative research. Start with a free trial today.

Sampling Techniques for Qualitative Research

• First Online: 27 October 2022

Cite this chapter

• Heather Douglas 4  

2725 Accesses

3 Citations

This chapter explains how to design suitable sampling strategies for qualitative research. The focus of this chapter is purposive (or theoretical) sampling to produce credible and trustworthy explanations of a phenomenon (a specific aspect of society). A specific research question (RQ) guides the methodology (the study design or approach ). It defines the participants, location, and actions to be used to answer the question. Qualitative studies use specific tools and techniques ( methods ) to sample people, organizations, or whatever is to be examined. The methodology guides the selection of tools and techniques for sampling, data analysis, quality assurance, etc. These all vary according to the purpose and design of the study and the RQ. In this chapter, a fake example is used to demonstrate how to apply your sampling strategy in a developing country.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Compact, lightweight edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info
• Durable hardcover edition

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Douglas, H. (2010). Divergent orientations in social entrepreneurship organisations. In K. Hockerts, J. Robinson, & J. Mair (Eds.), Values and opportunities in social entrepreneurship (pp. 71–95). Palgrave Macmillan.

Chapter   Google Scholar  

Douglas, H., Eti-Tofinga, B., & Singh, G. (2018a). Contextualising social enterprise in Fiji. Social Enterprise Journal, 14 (2), 208–224. https://doi.org/10.1108/SEJ-05-2017-0032

Article   Google Scholar  

Douglas, H., Eti-Tofinga, B., & Singh, G. (2018b). Hybrid organisations contributing to wellbeing in small Pacific island countries. Sustainability Accounting, Management and Policy Journal, 9 (4), 490–514. https://doi.org/10.1108/SAMPJ-08-2017-0081

Douglas, H., & Borbasi, S. (2009). Parental perspectives on disability: The story of Sam, Anna, and Marcus. Disabilities: Insights from across fields and around the world, 2 , 201–217.

Google Scholar  

Douglas, H. (1999). Community transport in rural Queensland: Using community resources effectively in small communities. Paper presented at the 5th National Rural Health Conference, Adelaide, South Australia, pp. 14–17th March.

Douglas, H. (2006). Action, blastoff, chaos: ABC of successful youth participation. Child, Youth and Environments, 16 (1). Retrieved from http://www.colorado.edu/journals/cye

Douglas, H. (2007). Methodological sampling issues for researching new nonprofit organisations. Paper presented at the 52nd International Council for Small Business (ICSB) 13–15 June, Turku, Finland.

Draper, H., Wilson, S., Flanagan, S., & Ives, J. (2009). Offering payments, reimbursement and incentives to patients and family doctors to encourage participation in research. Family Practice, 26 (3), 231–238. https://doi.org/10.1093/fampra/cmp011

Puamua, P. Q. (1999). Understanding Fijian under-achievement: An integrated perspective. Directions, 21 (2), 100–112.

Download references

Author information

Authors and affiliations.

The University of Queensland, The Royal Society of Queensland, Activation Australia, Brisbane, Australia

Heather Douglas

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Heather Douglas .

Editor information

Editors and affiliations.

Centre for Family and Child Studies, Research Institute of Humanities and Social Sciences, University of Sharjah, Sharjah, United Arab Emirates

M. Rezaul Islam

Department of Development Studies, University of Dhaka, Dhaka, Bangladesh

Niaz Ahmed Khan

Department of Social Work, School of Humanities, University of Johannesburg, Johannesburg, South Africa

Rajendra Baikady

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this chapter

Douglas, H. (2022). Sampling Techniques for Qualitative Research. In: Islam, M.R., Khan, N.A., Baikady, R. (eds) Principles of Social Research Methodology. Springer, Singapore. https://doi.org/10.1007/978-981-19-5441-2_29

Download citation

DOI : https://doi.org/10.1007/978-981-19-5441-2_29

Published : 27 October 2022

Publisher Name : Springer, Singapore

Print ISBN : 978-981-19-5219-7

Online ISBN : 978-981-19-5441-2

eBook Packages : Social Sciences

Share this chapter

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

• Research article
• Open access
• Published: 31 January 2019

Purposive sampling in a qualitative evidence synthesis: a worked example from a synthesis on parental perceptions of vaccination communication

• Heather Ames   ORCID: orcid.org/0000-0001-8509-7160 1 , 2 ,
• Claire Glenton 3 &
• Simon Lewin 4 , 5  

BMC Medical Research Methodology volume  19 , Article number:  26 ( 2019 ) Cite this article

217k Accesses

170 Citations

51 Altmetric

Metrics details

In a qualitative evidence synthesis, too much data due to a large number of studies can undermine our ability to perform a thorough analysis. Purposive sampling of primary studies for inclusion in the synthesis is one way of achieving a manageable amount of data. The objective of this article is to describe the development and application of a sampling framework for a qualitative evidence synthesis on vaccination communication.

We developed and applied a three-step framework to sample studies from among those eligible for inclusion in our synthesis. We aimed to prioritise studies that were from a range of settings, were as relevant as possible to the review, and had rich data. We extracted information from each study about country and study setting, vaccine, data richness, and study objectives and applied the following sampling framework:

Studies conducted in low and middle income settings

Studies scoring four or more on a 5-point scale of data richness

Studies where the study objectives closely matched our synthesis objectives

We assessed 79 studies as eligible for inclusion in the synthesis and sampled 38 of these. First, we sampled all nine studies that were from low and middle-income countries. These studies contributed to the least number of findings. We then sampled an additional 24 studies that scored high for data richness. These studies contributed to a larger number of findings. Finally, we sampled an additional five studies that most closely matched our synthesis objectives. These contributed to a large number of findings.

Conclusions

Our approach to purposive sampling helped ensure that we included studies representing a wide geographic spread, rich data and a focus that closely resembled our synthesis objective. It is possible that we may have overlooked primary studies that did not meet our sampling criteria but would have contributed to the synthesis. For example, two studies on migration and access to health services did not meet the sampling criteria but might have contributed to strengthening at least one finding. We need methods to cross-check for under-represented themes.

Peer Review reports

Qualitative evidence syntheses, also known as systematic reviews of qualitative research, aim to explore people’s perceptions and experiences of the world around them by synthesizing data from studies across a range of settings. When well-conducted, a qualitative evidence synthesis provides an in-depth understanding of complex phenomena while focusing on the experiences and perceptions of research participants and taking into consideration other contextual factors [ 1 ]. Qualitative evidence synthesis first appeared as a methodology in the health sciences in the mid-1990s [ 2 ]. The approach is still relatively rare compared to systematic reviews of intervention effectiveness, but is becoming more common [ 3 ], and organisations such as Cochrane are now undertaking these types of synthesis [ 4 , 5 , 6 ]. The ways in which these syntheses are conducted has evolved over the last 20 years and now includes a variety of approaches such as meta-ethnography, thematic analysis, narrative synthesis and realist synthesis [ 2 , 7 ].

For some qualitative evidence synthesis questions, there are a large number of primary qualitative studies available, and there are several examples of syntheses that include more than 50 studies [ 8 ]. However, in contrast to reviews of effectiveness, the inclusion of a large number of primary studies with a high volume of data is not necessarily viewed as an advantage as it can threaten the quality of the synthesis. There are a number of reasons for this: firstly, analysis of qualitative data requires a detailed engagement with text. However, large volumes of data make this difficult to achieve, and can make it difficult to move from descriptive or aggregative analysis to more interpretive analysis. Similar to the argument made for primary qualitative research [ 9 , 10 ], the more data a researcher has to synthesize, the less depth and richness they are likely to be able to extract from the data. Furthermore, effectiveness reviews aim to be exhaustive in order to achieve statistical generalizability which requires certain procedures whereas qualitative evidence synthesis aim to understand the phenomenon of interest and how it plays out in a context. This requires gathering data from the various contexts and respondent groups relevant to understanding the phenomenon. This is done in a purposeful way to gather data relevant to answering the review question. Exhaustive searching and inclusion can undermine this understanding, as qualitative synthesis seek to achieve conceptual and not statistical generalizability.

The sampling of studies within qualitative evidence syntheses is still a relatively new methodological strategy, but is generally based on the same principles as those used to conduct sampling within primary qualitative research [ 11 , 12 ]. There has been little written on how best to limit the number of included studies in a qualitative evidence synthesis and there is currently no agreement amongst review authors and methodologists about the best approach [ 13 ]. Options include sampling from the range of eligible studies (similar to purposively sampling participants within primary qualitative research) or narrowing the scope of the research question by, for example, geographic area or population. Suri [ 14 ] proposes a range of different strategies that could be applied to purposively sample for a qualitative evidence synthesis (see Table  1 for examples). These methods are adapted from a list by Patton for primary research purposes [ 12 ]. A recent paper by Benoot, Hannes et al. gives a worked example of sampling for a qualitative evidence synthesis [ 15 ]. However, there are few other well-described examples of the use of these approaches and it is not yet clear which approaches are best suited to particular kinds of synthesis, synthesis processes and questions.

The example of sampling for a qualitative evidence synthesis presented in this article is drawn from a Cochrane qualitative evidence synthesis on parents’ and informal caregivers’ views and experiences of communication about routine childhood vaccination [ 5 ]. We understood at an early stage that the number of studies eligible for this synthesis would be high. As there was limited guidance on how to sample studies for inclusion in a qualitative evidence synthesis, we had to explore ways of solving this methodological challenge. The objective of this paper is to discuss the development and application of a sampling framework for a qualitative evidence synthesis on vaccination communication and the lessons learnt.

The objective of our qualitative evidence synthesis was to identify, appraise and synthesise qualitative studies exploring parents’ and informal caregivers’ views and experiences regarding the communication they receive about childhood vaccinations and the manner in which they receive it [ 5 ]. To be eligible for inclusion in the synthesis, studies had to have used qualitative methods of data collection and analysis; had parents or informal caregivers as participants; and had a focus on views and experiences of information about childhood vaccination. In August 2016, we searched MEDLINE, Embase, CINAHL and Anthropology Plus for eligible studies. We chose these databases as we anticipated that they would provide the highest yield of results based on preliminary, exploratory searches [ 5 ].

Seventy-nine studies met our eligibility criteria. We decided that this number of included studies was too large to analyse adequately and discussed whether it would be reasonable to limit our synthesis to specific settings or certain types of childhood vaccines. However, we concluded that narrowing the scope of the synthesis was not an acceptable option as we were interested in identifying global patterns concerning parental preferences for information. We mapped the eligible studies by extracting key information from each study, including information about country, study setting, vaccine type, participants, research methods and study objectives. This mapping of the included studies also showed that it would be difficult to narrow by vaccine type as the majority of the studies did not state explicitly which vaccines the study encompassed but focused instead on parents’ and caregivers’ views on childhood vaccination communication in general. We therefore decided to sample from the included studies.

Our main aim when sampling studies was to protect the quality of our analysis by ensuring that the amount of data was manageable. However, we also wanted to ensure that the studies we sampled were the most suitable for answering our objectives. As this was a global review, we were looking for studies that covered a broad range of settings, including high, middle and low income countries. In addition, we wanted studies that were as close as possible to the topic of our synthesis and that had as rich data as possible.

When considering how to achieve these goals, we assessed all of the 16 purposeful sampling methods proposed in the Suri study [ 14 ]. However, none of these directly fit all of our needs although some of the methods addressed some of these needs (See Table  6 ). We therefore reshaped the approaches described in Suri, combining different sampling strategies to create our own purposive sampling framework, as has been done by others [ 15 ].

We developed the sampling framework taking into consideration the data that had been mapped from the included studies and what would best fit with our research objective. The sampling framework was piloted on a group of ten studies and the review authors discussed challenges that arose. Our final, three-step sampling framework was as follows:

Step 1: Sampling for maximum variation

Our focus was to develop a global understanding of the phenomenon of interest, including similarities and differences across different settings. The majority of the studies that met the inclusion criteria took place in high-income settings. Our first step was therefore to sample all studies from low and middle-income countries. This helped us to ensure a geographic spread and reasonable representation of findings from all income settings. The inclusion of these studies was also important because of the interest globally in improving vaccination uptake in these settings, and this was also part of the ‘Communicate to vaccinate’ project in which the synthesis was embedded [ 16 ].

Step 2: Sampling for data richness

Second, to ensure that we would have enough data for our synthesis, we focused on the richness of the data within the remaining included studies. We based this decision on the rationale that rich data can provide in-depth insights into the phenomenon of interest, allowing the researcher to better interpret the meaning and context of findings presented in the primary studies [ 17 ]. To our knowledge there is no existing tool to map data richness in qualitative studies. We therefore created a simple 1–5 scale for assessing data richness (see Table  2 ). After assessing the data richness of the remaining included studies, we sampled all studies that scored a 4 or higher for data richness.

Step 3: Sampling for study scope / sampling for match of scope

Finally, we anticipated that studies that closely matched our objectives were likely to include data that was most valuable for the synthesis, even if those data were not very rich. After applying the first two sampling steps, we therefore examined the studies that remained and sampled studies where the study findings and objectives most closely matched our synthesis objectives. Studies were eligible for inclusion in the synthesis if they included at least one theme regarding parental perceptions about vaccination communication. However, many of these studies focused on parental perceptions of vaccination or vaccination programs rather than on parental perceptions of vaccination communication more specifically. In this final sampling step, we looked for studies that had primarily focused on parental perceptions about vaccination information and communication but had not been sampled in the first two steps. For example, an article exploring what informs parents’ decision making about childhood vaccination [ 18 ] was not included in step 1 as it was not from a low or middle income country or in step 2 as it scored a 3 for data richness. It was sampled in step 3 as its focus on information closely matched to the synthesis objectives.

We listed studies that met our inclusion criteria but were not sampled into the analysis in a table in the published qualitative evidence synthesis. The table provided the reason why the study was not sampled. This table provides readers with an overview of the existing research literature, makes our decision making process transparent and allows readers to critically appraise our decisions.

After the qualitative evidence synthesis was completed, we mapped the step during which each study was sampled and the number of findings to which each study had contributed. (See Appendix 1) We did this to see if the step at which the study was sampled into the review had an impact on the number of findings it contributed to; allowing us to see if studies sampled for richer data or closeness to the review objective did actually contribute to more findings.

During the process of writing the qualitative evidence synthesis, the review authors continued to discuss the strengths and weaknesses of the approach used to identify the issues presented in this paper. We also presented the approach to other teams doing qualitative evidence syntheses, and at conferences and meetings. These presentations and ensuing discussions facilitated the identification of other strengths and weaknesses of the approach that we had used. (See Table 6 ).

Seventy-nine studies were eligible for inclusion in the synthesis. After applying our sampling framework, we included thirty-eight studies.

Our experiences when applying the sampling framework

The sampling approach we used in this review aimed to achieve a range of settings, studies with rich data and studies with findings that matched our review objective. We aimed to build a sampling framework that specifically addressed and was in harmony with the synthesis objectives.

Sampling means that we may miss articles with information about particular populations, settings, or interventions

One of the main challenges of using a sampling approach is that we are likely to have omitted data related to particular populations, settings, communication strategies, vaccines or experiences. However, we argue that this approach allowed us to achieve a good balance between the quality of the analysis and the range of settings and populations within the included studies. First we will present a challenge related to setting and second a challenge related to population.

The first challenge we addressed was related to study setting. Our sampling approach did not directly select studies conducted in high income countries, and this led to some studies from these settings not being sampled. However, we decided that geographic spread was an important factor for this global synthesis and sampled accordingly. This is a limitation of our sampling frame. However, we believe that it was a strength to have studies from a wider variety of settings to increase the relevance of the findings to a larger number of contexts.

The second challenge relates to study population. Our sampling frame did not directly sample for variation in study populations. One clear example of how studies were missed that could have directly contributed to a finding related to a specific study population came with the issue of migration and vaccination.

Finding 6: Parents who had migrated to a new country had difficulty negotiating the new health system and accessing and understanding vaccination information.

We did not sample a few primary studies that discussed migrant issues specifically, as they did not meet the sampling criteria; specifically, they were not from LMIC contexts, had thin data or did not closely match the synthesis objectives. They most likely would have contributed to strengthening at least the finding described above.

Our sampling framework meant that we may have sampled studies with thinner data

With our decision to focus on study location in step 1 of our sampling we may have sampled studies from low and middle-income contexts that scored a 1 or 2 for data richness (a potential weakness) and not sampled studies from high income settings with richer data. We were unsure whether the amount of relevant data in the studies from low and middle-income settings would make a contribution to the synthesis and findings. In the end we decided to include these studies to address the issue of relevance for LMIC contexts since the synthesis had a global perspective. However, this meant that studies with richer data from more privileged settings were not sampled. To adjust for this the second step of sampling was directly linked to data richness. All studies scoring a 4 or higher for data richness were sampled.

Making decisions on how to assess data richness?

Initially, we looked at the whole study when assessing data richness. However, we realised that much of this data covered topics that were outside of the scope of the synthesis. This included, for example, information on parents perceptions of vaccines in general, advice they had received from unofficial sources such as friends and neighbours and their thoughts about how susceptible their children were to vaccine preventable diseases.

We therefore adapted the data richness scale to combine steps 2 and 3 of our sampling framework. The end result was a table where the richness of data in an included study is not ranked by the total amount of data but by the amount of data that is relevant to the synthesis objectives (see Table  3 ). This approach has since been used successfully in a new synthesis (Ames HMR, Glenton C, Lewin S, Tamrat T, Akama E, Leon N: Patients and peoples’ perceptions and experiences of targeted digital communication accessible via mobile devices for reproductive, maternal, newborn, child and adolescent health: a qualitative evidence synthesis. Submitted).

Did the sampling step impact on how many findings a study contributed to?

It has been suggested that studies with richer data, also described as conceptual clarity, may self-weight in the findings of qualitative evidence syntheses (contribute more data to the synthesis) and be found to be more methodologically sound [ 19 , 20 ]. In order to test this we mapped the step in which the studies were sampled and the number of findings each study contributed to. The rationale for this was that we sampled studies that had a lower score for data richness in steps one and three. If these studies contributed to a distinctly lower number of study findings this could reinforce the idea that studies with richer data (i.e. step two) contributed more data to more findings than studies with thinner data. To some extent this was the case with the studies sampled in step one from low and middle-income contexts. However, this did not apply as well to studies sampled in step three where the study findings were more closely aligned with the synthesis objectives. (See Table  4 ).

Nine studies from LMIC contexts were sampled in step one and these contributed to, on average, the least number of synthesis findings. Twenty-four studies were sampled on the basis of data richness in step two; these contributed to a large number of findings. The five studies sampled in step three because their findings most closely matched the synthesis objectives also contributed to a large number of findings. Table 4 shows the overview of how many studies were sampled in each step and how many findings the studies contributed to (See additional file  1 for a detailed overview per study).

We believe that our sampling framework allowed us to limit the number of studies included in the synthesis in order to make analysis manageable, while still allowing us to achieve the objectives of the synthesis.

The decision to purposively sample primary studies for inclusion in the qualitative evidence synthesis had its strengths and weaknesses. It allowed us to achieve a sufficiently wide geographic spread of primary studies while limiting the number of studies included in the synthesis. It enabled us to include studies with rich data and studies that most closely resembled the synthesis objectives. However, we may have overlooked primary studies that did not meet the sampling criteria but would have contributed to the synthesis. Furthermore, this qualitative evidence synthesis used a thematic approach to synthesis. Different synthesis approaches may have led us towards different ways of sampling or have identified different findings.

The approach for assessing richness of data needs to be developed further and tested within other qualitative evidence syntheses to see if it needs adjustment. It has worked well for the two syntheses we have used it in and has been understandable to other authors as a logical tool for mapping how much relevant data is in each included study [ 21 ] (Ames HL N, Glenton C, Tamrat T, Lewin S: Patients’ and clients’ perceptions and experiences of targeted digital communication accessible via mobile devices for reproductive, maternal, newborn, child and adolescent health: a qualitative evidence synthesis (protocol), unpublished) . However, objective testing of the scale would be needed to assess its validity across research teams and to standardize its approach.

Working with the GRADE-CERQual approach to develop sampling for qualitative evidence synthesis in the future

Qualitative evidence syntheses are increasingly using GRADE-CERQual (hereafter referred to as CERQual) to assess the confidence in their findings. CERQual aims to transparently assess and describe how much confidence decision makers and other users can place in individual synthesis findings from syntheses of qualitative evidence. Confidence in the evidence has been defined as an assessment of the extent to which the synthesis finding is a reasonable representation of the phenomenon of interest. CERQual includes four components [ 22 , 23 ] (Table  5 ).

We believe that purposive sampling would be useful to address concerns that arise during the CERqual process, specifically regarding relevance and adequacy. However, all four components could be taken into consideration when developing a sampling frame.

Relevance addresses a number of study characteristics (see Additional file 2 ). It links to the approach we took in step 1 to include a maximum variation of settings. Review authors could use the relevance concept to design their sampling framework to address key study characteristics. A review author could also return to the pool of included studies and sample studies that would help to moderate downgrading in relation to these concepts. For example, if a synthesis finding was downgraded for relevance as all of the studies were conducted in a specific context or geographic location the authors could go back and sample studies from other contexts to address relevance concerns.

The adequacy component of CERQual links to our assessment of data richness. Is there enough data and rich data to support a synthesis finding? By sampling studies with richer data we believe that adequacy could be improved.

Related to the concepts of data richness and adequacy of data is the concept of data saturation. Our aim was not to reach data saturation for each of the findings in the synthesis through sampling. It would be possible to develop a sampling approach geared towards the concept of saturation however, this would be different from completing sampling before the analysis stage of the synthesis. If you were to sample with the aim of saturation it would be natural to sample from your included primary studies during the analysis process, in a sequential way.

Methodological limitations

A potential weakness of our approach is that we did not sample studies based on their methodological limitations. This means that primary studies that were methodologically weak may have been included in the synthesis if they met our sampling criteria. This has implications for our CERQual assessment of confidence in the evidence, as findings based on studies with important methodological limitations are likely to be downgraded. Future syntheses could include methodological limitations in a sampling framework. This could lead to higher confidence in some review findings. However, this approach could also potentially lead us to sample even fewer studies, which could have implications for other CERQual components, including our assessment of data adequacy or relevance. Another possible option is to identify findings that have been downgraded due to concerns about the methodological limitations of the contributing studies. Review authors could then choose to look at the pool of well conducted studies that have not been sampled to see if any include data that could contribute to the finding and could therefore be sampled into the synthesis. Further work is needed to explore the advantages and disadvantages of these different options.

A linked issue is that, to date, the best way in which to assess the methodological strengths and limitations of qualitative research is still contested [ 7 , 24 ]. We believe that assessing the methodological strengths and limitations of included studies is feasible and is an important aspect of engaging with the primary studies included in a synthesis [ 24 ]. We would also argue that most readers make judgements about the methodological strengths and limitations of qualitative studies that they are looking at, and that the tools available to assess this help to make these judgements more transparent and systematic. To be useful, these judgements need to be linked to the synthesis findings, as part of a CERQual assessment of confidence in the evidence.

Qualitative evidence synthesis updates

This type of purposive sampling could also be useful during synthesis updates. In this case, a review author could sample studies from the pool of included studies that would contribute to strengthening findings with very low or low confidence. Further work is needed to see how sampling processes and CERQual assessments impact on each other. In Table 6 we present different ways in which we believe different sampling methods could be used in future synthesis.

In conducting the sampling for this synthesis and talking with other qualitative evidence synthesis authors it has become clear that more research and guidance are needed around this topic. Review authors need to try out different sampling methods and approaches and document the steps they took and how the sampling approach worked out. It would be useful to conduct research comparing different sampling approaches for the same synthesis question and looking at whether these result in different findings. Finally, it is important that better guidance is developed for review authors on how to apply different sampling approaches when conducting a qualitative evidence synthesis.

We used purposive sampling to select 38 primary studies for the data synthesis using a three step-sampling frame. We employed a sampling strategy, as seventy-nine studies were eligible for inclusion in the synthesis. We feel that large numbers of studies can threaten the quality of the analysis in a qualitative evidence synthesis. We used the sampling strategy to decrease the number of studies to a manageable number.

Going forward, there is a need for research into purposive sampling for qualitative evidence synthesis to test the robustness of different sampling frameworks. More research also needs to be undertaken on how best to rate data richness within qualitative primary studies.

In conclusion, this systematic three-step approach to sampling may prove useful to other qualitative evidence synthesis authors. However, based on our experience it could be narrowed to a two-step approach with the combination of data richness and closeness to the synthesis objectives. Further steps could be added to address synthesis specific objectives such as population or intervention. As more syntheses are completed, the issue of sampling will arise more frequently and so approaches that are more explicit need to be developed. Transparent and tested approaches to sampling for synthesis of qualitative evidence are important to ensure the reliability and trustworthiness of synthesis findings.

Saini M, Shlonsky A. Systematic synthesis of qualitative research. USA: OUP; 2012.

Book   Google Scholar  

Thorne S. Metasynthetic madness: what kind of monster have we created? Qual Health Res. 2017;27(1):3–12.

Article   Google Scholar  

Noyes J, Booth A, Cargo M, Flemming K, Garside R, Hannes K, Harden A, Harris J, Lewin S, Pantoja T. Cochrane qualitative and implementation methods group guidance series-paper 1: introduction. J Clin Epidemiol. 2017.

Glenton C, Colvin CJ, Carlsen B, Swartz A, Lewin S, Noyes J, Rashidian A. Barriers and facilitators to the implementation of lay health worker programmes to improve access to maternal and child health: qualitative evidence synthesis. Cochrane Database Syst Rev. 2013;10(10).

Ames HM, Glenton C, Lewin S. Parents' and informal caregivers’ views and experiences of communication about routine childhood vaccination: a synthesis of qualitative evidence. Cochrane Libr. 2017.

Munabi-Babigumira SGC, Lewin S, Fretheim A, Nabudere H. Factors that influence the provision of intrapartum and postnatal care by skilled birth attendants in low- and middle-income countries: a qualitative evidence synthesis. Cochrane Database Syst Rev. 2017;11.

Noyes J, Booth A, Flemming K, Garside R, Harden A, Lewin S, Pantoja T, Hannes K, Cargo M, Thomas J. Cochrane Qualitative and Implementation Methods Group guidance series—paper 3: methods for assessing methodological limitations, data extraction and synthesis, and confidence in synthesized qualitative findings. J Clin Epidemiol. 2018;97:49–58.

Toye F, Seers K, Tierney S, Barker KL. A qualitative evidence synthesis to explore healthcare professionals’ experience of prescribing opioids to adults with chronic non-malignant pain. BMC Fam Pract. 2017;18(1):94.

Morse JM. Sampling in grounded theory. The SAGE handbook of grounded theory. 2010:229–44.

Sandelowski M. Sample size in qualitative research. Research in nursing & health. 1995;18(2):179–83.

Article   CAS   Google Scholar  

Silverman D. Doing qualitative research: a practical handbook: SAGE publications limited; 2013.

Quinn-Patton M. Qualitative research and evaluation methods. London: Sage Publications; 2002.

Google Scholar  

Tranfield D, Denyer D, Smart P. Towards a methodology for developing evidence-informed management knowledge by means of systematic review. Br J Manag. 2003;14(3):207–22.

Suri H. Purposeful sampling in qualitative research synthesis. Qual Res J. 2011;11(2):63–75.

Benoot C, Hannes K, Bilsen J. The use of purposeful sampling in a qualitative evidence synthesis: a worked example on sexual adjustment to a cancer trajectory. BMC Med Res Methodol. 2016;16(1):21.

The communicate to vaccinate project (COMMVAC) [ www.commvac.com ].

Popay J, Rogers A, Williams G. Rationale and standards for the systematic review of qualitative literature in health services research. Qual Health Res. 1998;8(3):341–51.

Austvoll-Dahlgren A, Helseth S. What informs parents’ decision-making about childhood vaccinations? J Adv Nurs. 2010;66(11):2421–30.

Atkins S, Lewin S, Smith H, Engel M, Fretheim A, Volmink J. Conducting a meta-ethnography of qualitative literature: lessons learnt. BMC Med Res Methodol. 2008;8(1):21.

Toye F, Seers K, Allcock N, Briggs M, Carr E, Andrews J, Barker K. ‘Trying to pin down jelly’-exploring intuitive processes in quality assessment for meta-ethnography. BMC Med Res Methodol. 2013;13(1):46.

Xyrichis A, Mackintosh NJ, Terblanche M, Bench S, Philippou J, Sandall J. Healthcare stakeholders’ perceptions and experiences of factors affecting the implementation of critical care telemedicine (CCT): qualitative evidence synthesis. Cochrane Libr. 2017.

Lewin S, Bohren M, Rashidian A, Munthe-Kaas H, Glenton C, Colvin CJ, Garside R, Noyes J, Booth A, Tunçalp Ö. Applying GRADE-CERQual to qualitative evidence synthesis findings—paper 2: how to make an overall CERQual assessment of confidence and create a summary of qualitative findings table. Implement Sci. 2018;13(1):10.

Lewin S, Glenton C, Munthe-Kaas H, Carlsen B, Colvin CJ, Gülmezoglu M, Noyes J, Booth A, Garside R, Rashidian A. Using qualitative evidence in decision making for health and social interventions: an approach to assess confidence in findings from qualitative evidence syntheses (GRADE-CERQual). PLoS Med. 2015;12(10):e1001895.

Noyes J, Booth A, Flemming K, Garside R, Harden A, Lewin S, Pantoja T, Hannes K, Cargo M, Thomas J. Cochrane qualitative and implementation methods group guidance series—paper 3: methods for assessing methodological limitations, data extraction and synthesis, and confidence in synthesized qualitative findings. J Clin Epidemiol. 2018;97:49–58.

Download references

Acknowledgements

Not applicable.

The original synthesis was funded by the Research Council of Norway. This paper has been funded by EPOC Norway as part of the Norwegian Institute of Public Health.

Availability of data and materials

All data generated or analysed during this study are included in this published article.

Author information

Authors and affiliations.

Cochrane Consumers and Communication Group, La Trobe University, Melbourne, Australia

Heather Ames

Division for Health Services, Norwegian Institute of Public Health, Postboks 222 Skøyen, Sandakerveien 24C, inngang D11, 0213, Oslo, Norway

Cochrane Norway and the Informed Health Choices Research Centre, Norwegian Institute of Public Health, Postboks 222 Skøyen, Sandakerveien 24C, inngang D11, 0213, Oslo, Norway

Claire Glenton

Cochrane EPOC group and the Informed Health Choices Research Centre, Norwegian Institute of Public Health, Postboks 222 Skøyen, Sandakerveien 24C, inngang D11, 0213, Oslo, Norway

Simon Lewin

Health Systems Research Unit, South African Medical Research Council, Tygerberg, South Africa

You can also search for this author in PubMed   Google Scholar

Contributions

HA wrote the draft of this paper with comment from CG and SL. All three are authors of the original qualitative evidence synthesis and were involved in developing the sampling framework and sampling from the included studies. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Heather Ames .

Ethics declarations

Ethics approval and consent to participate, consent for publication, competing interests.

The authors declare that they have no competing interests.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Additional files

Additional file 1:.

Overview of sampling stage and contribution to findings for primary studies included in the Qualitative Evidence Synthesis . This table presents an overview of each of the primary studies included in the qualitative evidence synthesis, the stage at which they were sampled and how many findings each study contributes to. (DOCX 13 kb)

Additional file 2:

Study characteristics addressed in the CERQual concept of relevance. This table presents the different study charachteristics that can be addresses when applying the CERQual concept of relevance. (DOCX 16 kb)

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License ( http://creativecommons.org/licenses/by/4.0/ ), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated.

Reprints and permissions

About this article

Cite this article.

Ames, H., Glenton, C. & Lewin, S. Purposive sampling in a qualitative evidence synthesis: a worked example from a synthesis on parental perceptions of vaccination communication. BMC Med Res Methodol 19 , 26 (2019). https://doi.org/10.1186/s12874-019-0665-4

Download citation

Received : 26 September 2018

Accepted : 14 January 2019

Published : 31 January 2019

DOI : https://doi.org/10.1186/s12874-019-0665-4

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Purposive sampling
• Qualitative evidence synthesis
• Systematic review

BMC Medical Research Methodology

ISSN: 1471-2288

• General enquiries: [email protected]

Purposive sampling

Purposive sampling (also known as  judgment, selective or subjective sampling) is a sampling technique in which researcher relies on his or her own judgment when choosing members of population to participate in the study.

Purposive sampling is a non-probability sampling method and it occurs when “elements selected for the sample are chosen by the judgment of the researcher. Researchers often believe that they can obtain a representative sample by using a sound judgment, which will result in saving time and money”. [1]

TV reporters stopping certain individuals on the street in order to ask their opinions about certain political changes constitutes the most popular example of this sampling method. However, it is important to specify that the TV reporter has to apply certain judgment when deciding who to stop on the street to ask questions; otherwise it would be the case of  random sampling  technique.

Alternatively, purposive sampling method may prove to be effective when only limited numbers of people can serve as primary data sources due to the nature of research design and aims and objectives. For example, for a research analysing affects of personal tragedy such as family bereavement on performance of senior level managers the researcher may use his/her own judgment in order to choose senior level managers who could particulate in in-depth interviews.

In purposive sampling personal judgment needs to be used to choose cases that help answer research questions or achieve research objectives.

According to the type of cases, purposive sampling can be divided into the following six categories [1] :

• Typical case . Explains cases that are average and normal.
• Extreme or deviant case . Deriving samples from cases that are perceived as unusual or rare such as exploring the reasons for corporate failure by interviewing executives that have been fired by shareholders.
• Critical case sampling focuses on specific cases that are dramatic or very important.
• Heterogeneous or maximum variation sampling relies on researcher’s judgment to select participants with diverse characteristics. This is done to ensure the presence of maximum variability within the primary data.
• Homogeneous sampling focuses on “focuses on one particular subgroup in which all the sample members are similar, such as a particular occupation or level in an organization’s hierarchy” [2]
• Theoretical sampling is a special case of purposive sampling that is based on an inductive method of Grounded Theory.

Application of Purposive Sampling (Judgment Sampling): an Example

Suppose, your dissertation topic has been approved as the following:

A study into the impact of tax scandal on the brand image of Starbucks Coffee in the UK

If you decide to apply questionnaire primary data collection method with use of purposive sampling, you can go out to Oxford Street and stop what seems like a reasonable cross-section of people in the street to survey.

Another example. Your research objective is to determine the patterns of use of social media by global IT consulting companies based in the US. Rather than applying random sampling and choosing subjects who may not be available, you can use purposive sampling to choose IT companies whose availability and attitude are compatible with the study.

Advantages of Purposive Sampling (Judgment Sampling)

• Purposive sampling is one of the most cost-effective and time-effective sampling methods available
• Purposive sampling may be the only appropriate method available if there are only limited number of primary data sources who can contribute to the study
• This sampling technique can be effective in exploring anthropological situations where the discovery of meaning can benefit from an intuitive approach

Disadvantages of Purposive Sampling (Judgment Sampling)

• Vulnerability to errors in judgment by researcher
• Low level of reliability and high levels of bias.
• Inability to generalize research findings

Because of these disadvantages purposive sampling (judgment sampling) method is not very popular in business studies, and the majority of dissertation supervisors usually do advice selecting alternative sampling methods with higher levels of reliability and low bias such as  quota ,  cluster , and  systematic  sampling methods…

My e-book,  The Ultimate Guide to Writing a Dissertation in Business Studies: a step by step approach  contains a detailed, yet simple explanation of  sampling methods . The e-book explains all stages of the  research process  starting from the  selection of the research area  to writing personal reflection. Important elements of dissertations such as  research philosophy ,  research approach ,  research design ,  methods of data collection  and  data analysis  are explained in this e-book in simple words.

John Dudovskiy

[1] Black, K. (2010) “Business Statistics: Contemporary Decision Making” 6 th  edition, John Wiley & Sons

[2] Saunders, M., Lewis, P. & Thornhill, A. (2012) “Research Methods for Business Students” 6 th  edition, Pearson Education Limited

[3] Saunders, M., Lewis, P. & Thornhill, A. (2012) “Research Methods for Business Students” 6 th  edition, Pearson Education Limited p.288

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Int J Prev Med

Qualitative Methods in Health Care Research

Vishnu renjith.

School of Nursing and Midwifery, Royal College of Surgeons Ireland - Bahrain (RCSI Bahrain), Al Sayh Muharraq Governorate, Bahrain

Renjulal Yesodharan

1 Department of Mental Health Nursing, Manipal College of Nursing Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India

Judith A. Noronha

2 Department of OBG Nursing, Manipal College of Nursing Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India

Elissa Ladd

3 School of Nursing, MGH Institute of Health Professions, Boston, USA

Anice George

4 Department of Child Health Nursing, Manipal College of Nursing Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India

Healthcare research is a systematic inquiry intended to generate robust evidence about important issues in the fields of medicine and healthcare. Qualitative research has ample possibilities within the arena of healthcare research. This article aims to inform healthcare professionals regarding qualitative research, its significance, and applicability in the field of healthcare. A wide variety of phenomena that cannot be explained using the quantitative approach can be explored and conveyed using a qualitative method. The major types of qualitative research designs are narrative research, phenomenological research, grounded theory research, ethnographic research, historical research, and case study research. The greatest strength of the qualitative research approach lies in the richness and depth of the healthcare exploration and description it makes. In health research, these methods are considered as the most humanistic and person-centered way of discovering and uncovering thoughts and actions of human beings.

Introduction

Healthcare research is a systematic inquiry intended to generate trustworthy evidence about issues in the field of medicine and healthcare. The three principal approaches to health research are the quantitative, the qualitative, and the mixed methods approach. The quantitative research method uses data, which are measures of values and counts and are often described using statistical methods which in turn aids the researcher to draw inferences. Qualitative research incorporates the recording, interpreting, and analyzing of non-numeric data with an attempt to uncover the deeper meanings of human experiences and behaviors. Mixed methods research, the third methodological approach, involves collection and analysis of both qualitative and quantitative information with an objective to solve different but related questions, or at times the same questions.[ 1 , 2 ]

In healthcare, qualitative research is widely used to understand patterns of health behaviors, describe lived experiences, develop behavioral theories, explore healthcare needs, and design interventions.[ 1 , 2 , 3 ] Because of its ample applications in healthcare, there has been a tremendous increase in the number of health research studies undertaken using qualitative methodology.[ 4 , 5 ] This article discusses qualitative research methods, their significance, and applicability in the arena of healthcare.

Qualitative Research

Diverse academic and non-academic disciplines utilize qualitative research as a method of inquiry to understand human behavior and experiences.[ 6 , 7 ] According to Munhall, “Qualitative research involves broadly stated questions about human experiences and realities, studied through sustained contact with the individual in their natural environments and producing rich, descriptive data that will help us to understand those individual's experiences.”[ 8 ]

Significance of Qualitative Research

The qualitative method of inquiry examines the 'how' and 'why' of decision making, rather than the 'when,' 'what,' and 'where.'[ 7 ] Unlike quantitative methods, the objective of qualitative inquiry is to explore, narrate, and explain the phenomena and make sense of the complex reality. Health interventions, explanatory health models, and medical-social theories could be developed as an outcome of qualitative research.[ 9 ] Understanding the richness and complexity of human behavior is the crux of qualitative research.

Differences between Quantitative and Qualitative Research

The quantitative and qualitative forms of inquiry vary based on their underlying objectives. They are in no way opposed to each other; instead, these two methods are like two sides of a coin. The critical differences between quantitative and qualitative research are summarized in Table 1 .[ 1 , 10 , 11 ]

Differences between quantitative and qualitative research

Qualitative Research Questions and Purpose Statements

Qualitative questions are exploratory and are open-ended. A well-formulated study question forms the basis for developing a protocol, guides the selection of design, and data collection methods. Qualitative research questions generally involve two parts, a central question and related subquestions. The central question is directed towards the primary phenomenon under study, whereas the subquestions explore the subareas of focus. It is advised not to have more than five to seven subquestions. A commonly used framework for designing a qualitative research question is the 'PCO framework' wherein, P stands for the population under study, C stands for the context of exploration, and O stands for the outcome/s of interest.[ 12 ] The PCO framework guides researchers in crafting a focused study question.

Example: In the question, “What are the experiences of mothers on parenting children with Thalassemia?”, the population is “mothers of children with Thalassemia,” the context is “parenting children with Thalassemia,” and the outcome of interest is “experiences.”

The purpose statement specifies the broad focus of the study, identifies the approach, and provides direction for the overall goal of the study. The major components of a purpose statement include the central phenomenon under investigation, the study design and the population of interest. Qualitative research does not require a-priori hypothesis.[ 13 , 14 , 15 ]

Example: Borimnejad et al . undertook a qualitative research on the lived experiences of women suffering from vitiligo. The purpose of this study was, “to explore lived experiences of women suffering from vitiligo using a hermeneutic phenomenological approach.” [ 16 ]

Review of the Literature

In quantitative research, the researchers do an extensive review of scientific literature prior to the commencement of the study. However, in qualitative research, only a minimal literature search is conducted at the beginning of the study. This is to ensure that the researcher is not influenced by the existing understanding of the phenomenon under the study. The minimal literature review will help the researchers to avoid the conceptual pollution of the phenomenon being studied. Nonetheless, an extensive review of the literature is conducted after data collection and analysis.[ 15 ]

Reflexivity

Reflexivity refers to critical self-appraisal about one's own biases, values, preferences, and preconceptions about the phenomenon under investigation. Maintaining a reflexive diary/journal is a widely recognized way to foster reflexivity. According to Creswell, “Reflexivity increases the credibility of the study by enhancing more neutral interpretations.”[ 7 ]

Types of Qualitative Research Designs

The qualitative research approach encompasses a wide array of research designs. The words such as types, traditions, designs, strategies of inquiry, varieties, and methods are used interchangeably. The major types of qualitative research designs are narrative research, phenomenological research, grounded theory research, ethnographic research, historical research, and case study research.[ 1 , 7 , 10 ]

Narrative research

Narrative research focuses on exploring the life of an individual and is ideally suited to tell the stories of individual experiences.[ 17 ] The purpose of narrative research is to utilize 'story telling' as a method in communicating an individual's experience to a larger audience.[ 18 ] The roots of narrative inquiry extend to humanities including anthropology, literature, psychology, education, history, and sociology. Narrative research encompasses the study of individual experiences and learning the significance of those experiences. The data collection procedures include mainly interviews, field notes, letters, photographs, diaries, and documents collected from one or more individuals. Data analysis involves the analysis of the stories or experiences through “re-storying of stories” and developing themes usually in chronological order of events. Rolls and Payne argued that narrative research is a valuable approach in health care research, to gain deeper insight into patient's experiences.[ 19 ]

Example: Karlsson et al . undertook a narrative inquiry to “explore how people with Alzheimer's disease present their life story.” Data were collected from nine participants. They were asked to describe about their life experiences from childhood to adulthood, then to current life and their views about the future life. [ 20 ]

Phenomenological research

Phenomenology is a philosophical tradition developed by German philosopher Edmond Husserl. His student Martin Heidegger did further developments in this methodology. It defines the 'essence' of individual's experiences regarding a certain phenomenon.[ 1 ] The methodology has its origin from philosophy, psychology, and education. The purpose of qualitative research is to understand the people's everyday life experiences and reduce it into the central meaning or the 'essence of the experience'.[ 21 , 22 ] The unit of analysis of phenomenology is the individuals who have had similar experiences of the phenomenon. Interviews with individuals are mainly considered for the data collection, though, documents and observations are also useful. Data analysis includes identification of significant meaning elements, textural description (what was experienced), structural description (how was it experienced), and description of 'essence' of experience.[ 1 , 7 , 21 ] The phenomenological approach is further divided into descriptive and interpretive phenomenology. Descriptive phenomenology focuses on the understanding of the essence of experiences and is best suited in situations that need to describe the lived phenomenon. Hermeneutic phenomenology or Interpretive phenomenology moves beyond the description to uncover the meanings that are not explicitly evident. The researcher tries to interpret the phenomenon, based on their judgment rather than just describing it.[ 7 , 21 , 22 , 23 , 24 ]

Example: A phenomenological study conducted by Cornelio et al . aimed at describing the lived experiences of mothers in parenting children with leukemia. Data from ten mothers were collected using in-depth semi-structured interviews and were analyzed using Husserl's method of phenomenology. Themes such as “pivotal moment in life”, “the experience of being with a seriously ill child”, “having to keep distance with the relatives”, “overcoming the financial and social commitments”, “responding to challenges”, “experience of faith as being key to survival”, “health concerns of the present and future”, and “optimism” were derived. The researchers reported the essence of the study as “chronic illness such as leukemia in children results in a negative impact on the child and on the mother.” [ 25 ]

Grounded Theory Research

Grounded theory has its base in sociology and propagated by two sociologists, Barney Glaser, and Anselm Strauss.[ 26 ] The primary purpose of grounded theory is to discover or generate theory in the context of the social process being studied. The major difference between grounded theory and other approaches lies in its emphasis on theory generation and development. The name grounded theory comes from its ability to induce a theory grounded in the reality of study participants.[ 7 , 27 ] Data collection in grounded theory research involves recording interviews from many individuals until data saturation. Constant comparative analysis, theoretical sampling, theoretical coding, and theoretical saturation are unique features of grounded theory research.[ 26 , 27 , 28 ] Data analysis includes analyzing data through 'open coding,' 'axial coding,' and 'selective coding.'[ 1 , 7 ] Open coding is the first level of abstraction, and it refers to the creation of a broad initial range of categories, axial coding is the procedure of understanding connections between the open codes, whereas selective coding relates to the process of connecting the axial codes to formulate a theory.[ 1 , 7 ] Results of the grounded theory analysis are supplemented with a visual representation of major constructs usually in the form of flow charts or framework diagrams. Quotations from the participants are used in a supportive capacity to substantiate the findings. Strauss and Corbin highlights that “the value of the grounded theory lies not only in its ability to generate a theory but also to ground that theory in the data.”[ 27 ]

Example: Williams et al . conducted a grounded theory research to explore the nature of relationship between the sense of self and the eating disorders. Data were collected form 11 women with a lifetime history of Anorexia Nervosa and were analyzed using the grounded theory methodology. Analysis led to the development of a theoretical framework on the nature of the relationship between the self and Anorexia Nervosa. [ 29 ]

Ethnographic research

Ethnography has its base in anthropology, where the anthropologists used it for understanding the culture-specific knowledge and behaviors. In health sciences research, ethnography focuses on narrating and interpreting the health behaviors of a culture-sharing group. 'Culture-sharing group' in an ethnography represents any 'group of people who share common meanings, customs or experiences.' In health research, it could be a group of physicians working in rural care, a group of medical students, or it could be a group of patients who receive home-based rehabilitation. To understand the cultural patterns, researchers primarily observe the individuals or group of individuals for a prolonged period of time.[ 1 , 7 , 30 ] The scope of ethnography can be broad or narrow depending on the aim. The study of more general cultural groups is termed as macro-ethnography, whereas micro-ethnography focuses on more narrowly defined cultures. Ethnography is usually conducted in a single setting. Ethnographers collect data using a variety of methods such as observation, interviews, audio-video records, and document reviews. A written report includes a detailed description of the culture sharing group with emic and etic perspectives. When the researcher reports the views of the participants it is called emic perspectives and when the researcher reports his or her views about the culture, the term is called etic.[ 7 ]

Example: The aim of the ethnographic study by LeBaron et al . was to explore the barriers to opioid availability and cancer pain management in India. The researchers collected data from fifty-nine participants using in-depth semi-structured interviews, participant observation, and document review. The researchers identified significant barriers by open coding and thematic analysis of the formal interview. [ 31 ]

Historical research

Historical research is the “systematic collection, critical evaluation, and interpretation of historical evidence”.[ 1 ] The purpose of historical research is to gain insights from the past and involves interpreting past events in the light of the present. The data for historical research are usually collected from primary and secondary sources. The primary source mainly includes diaries, first hand information, and writings. The secondary sources are textbooks, newspapers, second or third-hand accounts of historical events and medical/legal documents. The data gathered from these various sources are synthesized and reported as biographical narratives or developmental perspectives in chronological order. The ideas are interpreted in terms of the historical context and significance. The written report describes 'what happened', 'how it happened', 'why it happened', and its significance and implications to current clinical practice.[ 1 , 10 ]

Example: Lubold (2019) analyzed the breastfeeding trends in three countries (Sweden, Ireland, and the United States) using a historical qualitative method. Through analysis of historical data, the researcher found that strong family policies, adherence to international recommendations and adoption of baby-friendly hospital initiative could greatly enhance the breastfeeding rates. [ 32 ]

Case study research

Case study research focuses on the description and in-depth analysis of the case(s) or issues illustrated by the case(s). The design has its origin from psychology, law, and medicine. Case studies are best suited for the understanding of case(s), thus reducing the unit of analysis into studying an event, a program, an activity or an illness. Observations, one to one interviews, artifacts, and documents are used for collecting the data, and the analysis is done through the description of the case. From this, themes and cross-case themes are derived. A written case study report includes a detailed description of one or more cases.[ 7 , 10 ]

Example: Perceptions of poststroke sexuality in a woman of childbearing age was explored using a qualitative case study approach by Beal and Millenbrunch. Semi structured interview was conducted with a 36- year mother of two children with a history of Acute ischemic stroke. The data were analyzed using an inductive approach. The authors concluded that “stroke during childbearing years may affect a woman's perception of herself as a sexual being and her ability to carry out gender roles”. [ 33 ]

Sampling in Qualitative Research

Qualitative researchers widely use non-probability sampling techniques such as purposive sampling, convenience sampling, quota sampling, snowball sampling, homogeneous sampling, maximum variation sampling, extreme (deviant) case sampling, typical case sampling, and intensity sampling. The selection of a sampling technique depends on the nature and needs of the study.[ 34 , 35 , 36 , 37 , 38 , 39 , 40 ] The four widely used sampling techniques are convenience sampling, purposive sampling, snowball sampling, and intensity sampling.

Convenience sampling

It is otherwise called accidental sampling, where the researchers collect data from the subjects who are selected based on accessibility, geographical proximity, ease, speed, and or low cost.[ 34 ] Convenience sampling offers a significant benefit of convenience but often accompanies the issues of sample representation.

Purposive sampling

Purposive or purposeful sampling is a widely used sampling technique.[ 35 ] It involves identifying a population based on already established sampling criteria and then selecting subjects who fulfill that criteria to increase the credibility. However, choosing information-rich cases is the key to determine the power and logic of purposive sampling in a qualitative study.[ 1 ]

Snowball sampling

The method is also known as 'chain referral sampling' or 'network sampling.' The sampling starts by having a few initial participants, and the researcher relies on these early participants to identify additional study participants. It is best adopted when the researcher wishes to study the stigmatized group, or in cases, where findings of participants are likely to be difficult by ordinary means. Respondent ridden sampling is an improvised version of snowball sampling used to find out the participant from a hard-to-find or hard-to-study population.[ 37 , 38 ]

Intensity sampling

The process of identifying information-rich cases that manifest the phenomenon of interest is referred to as intensity sampling. It requires prior information, and considerable judgment about the phenomenon of interest and the researcher should do some preliminary investigations to determine the nature of the variation. Intensity sampling will be done once the researcher identifies the variation across the cases (extreme, average and intense) and picks the intense cases from them.[ 40 ]

Deciding the Sample Size

A-priori sample size calculation is not undertaken in the case of qualitative research. Researchers collect the data from as many participants as possible until they reach the point of data saturation. Data saturation or the point of redundancy is the stage where the researcher no longer sees or hears any new information. Data saturation gives the idea that the researcher has captured all possible information about the phenomenon of interest. Since no further information is being uncovered as redundancy is achieved, at this point the data collection can be stopped. The objective here is to get an overall picture of the chronicle of the phenomenon under the study rather than generalization.[ 1 , 7 , 41 ]

Data Collection in Qualitative Research

The various strategies used for data collection in qualitative research includes in-depth interviews (individual or group), focus group discussions (FGDs), participant observation, narrative life history, document analysis, audio materials, videos or video footage, text analysis, and simple observation. Among all these, the three popular methods are the FGDs, one to one in-depth interviews and the participant observation.

FGDs are useful in eliciting data from a group of individuals. They are normally built around a specific topic and are considered as the best approach to gather data on an entire range of responses to a topic.[ 42 Group size in an FGD ranges from 6 to 12. Depending upon the nature of participants, FGDs could be homogeneous or heterogeneous.[ 1 , 14 ] One to one in-depth interviews are best suited to obtain individuals' life histories, lived experiences, perceptions, and views, particularly while exporting topics of sensitive nature. In-depth interviews can be structured, unstructured, or semi-structured. However, semi-structured interviews are widely used in qualitative research. Participant observations are suitable for gathering data regarding naturally occurring behaviors.[ 1 ]

Data Analysis in Qualitative Research

Various strategies are employed by researchers to analyze data in qualitative research. Data analytic strategies differ according to the type of inquiry. A general content analysis approach is described herewith. Data analysis begins by transcription of the interview data. The researcher carefully reads data and gets a sense of the whole. Once the researcher is familiarized with the data, the researcher strives to identify small meaning units called the 'codes.' The codes are then grouped based on their shared concepts to form the primary categories. Based on the relationship between the primary categories, they are then clustered into secondary categories. The next step involves the identification of themes and interpretation to make meaning out of data. In the results section of the manuscript, the researcher describes the key findings/themes that emerged. The themes can be supported by participants' quotes. The analytical framework used should be explained in sufficient detail, and the analytic framework must be well referenced. The study findings are usually represented in a schematic form for better conceptualization.[ 1 , 7 ] Even though the overall analytical process remains the same across different qualitative designs, each design such as phenomenology, ethnography, and grounded theory has design specific analytical procedures, the details of which are out of the scope of this article.

Computer-Assisted Qualitative Data Analysis Software (CAQDAS)

Until recently, qualitative analysis was done either manually or with the help of a spreadsheet application. Currently, there are various software programs available which aid researchers to manage qualitative data. CAQDAS is basically data management tools and cannot analyze the qualitative data as it lacks the ability to think, reflect, and conceptualize. Nonetheless, CAQDAS helps researchers to manage, shape, and make sense of unstructured information. Open Code, MAXQDA, NVivo, Atlas.ti, and Hyper Research are some of the widely used qualitative data analysis software.[ 14 , 43 ]

Reporting Guidelines

Consolidated Criteria for Reporting Qualitative Research (COREQ) is the widely used reporting guideline for qualitative research. This 32-item checklist assists researchers in reporting all the major aspects related to the study. The three major domains of COREQ are the 'research team and reflexivity', 'study design', and 'analysis and findings'.[ 44 , 45 ]

Critical Appraisal of Qualitative Research

Various scales are available to critical appraisal of qualitative research. The widely used one is the Critical Appraisal Skills Program (CASP) Qualitative Checklist developed by CASP network, UK. This 10-item checklist evaluates the quality of the study under areas such as aims, methodology, research design, ethical considerations, data collection, data analysis, and findings.[ 46 ]

Ethical Issues in Qualitative Research

A qualitative study must be undertaken by grounding it in the principles of bioethics such as beneficence, non-maleficence, autonomy, and justice. Protecting the participants is of utmost importance, and the greatest care has to be taken while collecting data from a vulnerable research population. The researcher must respect individuals, families, and communities and must make sure that the participants are not identifiable by their quotations that the researchers include when publishing the data. Consent for audio/video recordings must be obtained. Approval to be in FGDs must be obtained from the participants. Researchers must ensure the confidentiality and anonymity of the transcripts/audio-video records/photographs/other data collected as a part of the study. The researchers must confirm their role as advocates and proceed in the best interest of all participants.[ 42 , 47 , 48 ]

Rigor in Qualitative Research

The demonstration of rigor or quality in the conduct of the study is essential for every research method. However, the criteria used to evaluate the rigor of quantitative studies are not be appropriate for qualitative methods. Lincoln and Guba (1985) first outlined the criteria for evaluating the qualitative research often referred to as “standards of trustworthiness of qualitative research”.[ 49 ] The four components of the criteria are credibility, transferability, dependability, and confirmability.

Credibility refers to confidence in the 'truth value' of the data and its interpretation. It is used to establish that the findings are true, credible and believable. Credibility is similar to the internal validity in quantitative research.[ 1 , 50 , 51 ] The second criterion to establish the trustworthiness of the qualitative research is transferability, Transferability refers to the degree to which the qualitative results are applicability to other settings, population or contexts. This is analogous to the external validity in quantitative research.[ 1 , 50 , 51 ] Lincoln and Guba recommend authors provide enough details so that the users will be able to evaluate the applicability of data in other contexts.[ 49 ] The criterion of dependability refers to the assumption of repeatability or replicability of the study findings and is similar to that of reliability in quantitative research. The dependability question is 'Whether the study findings be repeated of the study is replicated with the same (similar) cohort of participants, data coders, and context?'[ 1 , 50 , 51 ] Confirmability, the fourth criteria is analogous to the objectivity of the study and refers the degree to which the study findings could be confirmed or corroborated by others. To ensure confirmability the data should directly reflect the participants' experiences and not the bias, motivations, or imaginations of the inquirer.[ 1 , 50 , 51 ] Qualitative researchers should ensure that the study is conducted with enough rigor and should report the measures undertaken to enhance the trustworthiness of the study.

Conclusions

Qualitative research studies are being widely acknowledged and recognized in health care practice. This overview illustrates various qualitative methods and shows how these methods can be used to generate evidence that informs clinical practice. Qualitative research helps to understand the patterns of health behaviors, describe illness experiences, design health interventions, and develop healthcare theories. The ultimate strength of the qualitative research approach lies in the richness of the data and the descriptions and depth of exploration it makes. Hence, qualitative methods are considered as the most humanistic and person-centered way of discovering and uncovering thoughts and actions of human beings.

Financial support and sponsorship

Conflicts of interest.

There are no conflicts of interest.