03 · What You Need to Know
Establishing a Defensible Qualitative Sample Size
Why Is Qualitative Sample Size Determined Differently From Quantitative Sample Size?
Quantitative sample-size calculations often focus on statistical power, estimation precision, variability, and sampling error under specified models.
Qualitative research commonly addresses different objectives. Researchers may seek to understand experiences, interpret meanings, examine social processes, develop theoretical explanations, or investigate how particular practices operate in context.
Consequently, the number of participants cannot ordinarily be determined by inserting a population size and margin of error into a statistical formula.
Qualitative adequacy is instead evaluated in relation to the information the data provide and the claims the analysis intends to make.
This does not mean that participant numbers are irrelevant. A poorly justified sample can restrict variation, leave important experiences unexplored, or create more material than the researcher can analyze adequately.
Does Every Qualitative Methodology Use the Same Sampling Logic?
No. The appropriate sampling strategy and criteria for adequacy depend on the methodological tradition.
| Qualitative approach |
Primary sampling consideration |
Implication for sample size |
| Phenomenological research |
Participants' experience of the phenomenon and the depth of its interpretation. |
A focused sample may support detailed analysis, depending on the phenomenological tradition. |
| Grounded theory |
Theoretical sampling and the development of conceptual categories. |
Recruitment may evolve as emerging analysis identifies further theoretical questions. |
| Case study |
Case boundaries, embedded units, and multiple sources of evidence. |
The number of cases and the number of participants within cases require separate justification. |
| Ethnography |
Field engagement, social relationships, observation, and contextual understanding. |
Participant count alone may be a poor indicator of data adequacy. |
| Qualitative descriptive research |
Coverage of experiences and perspectives relevant to a defined descriptive aim. |
Sample size depends on participant diversity, scope, and analytical needs. |
| Reflexive thematic analysis |
Interpretive engagement with data and the depth of theme development. |
Sample justification should be consistent with the approach's assumptions rather than automatically invoking saturation. |
These are broad methodological distinctions, not fixed rules. For example, phenomenology includes traditions with different philosophical commitments, while thematic analysis encompasses approaches that do not share identical assumptions about coding or saturation.
Researchers should explain why their sampling decisions are consistent with the specific methodology they claim to use.
How Does the Research Aim Affect the Number of Participants?
A narrowly focused research aim may require fewer participants than a broad investigation involving substantially different contexts or experiences.
Consider two studies. One examines how experienced online instructors at a particular university interpret a specific assessment policy. The other investigates how teachers across multiple educational levels, disciplines, and institutions experience artificial intelligence in teaching.
The second study may need broader sampling to address its intended variation.
However, a narrow aim does not automatically guarantee that a small sample will be sufficient. The phenomenon may be complex, the participants may provide limited information, or the analysis may require additional perspectives.
The relationship between research aim and qualitative sample size should therefore be assessed alongside the other features of the design.
What Is Information Power?
Malterud, Siersma, and Guassora (2016) proposed information power as an approach to considering sample adequacy in qualitative interview studies.
The central proposition is that a sample containing information particularly relevant to the study's aim may require fewer participants than one offering less relevant information.
The authors identify five interacting considerations: the study aim, sample specificity, use of established theory, quality of dialogue, and analysis strategy.
These considerations should be assessed together rather than converted into a mechanical scoring system.
| Information power consideration |
Question for the researcher |
| Study aim |
Is the investigation narrowly focused or broadly exploratory? |
| Sample specificity |
Do participants have experiences particularly relevant to the phenomenon? |
| Established theory |
Does an appropriate theoretical perspective help focus the inquiry? |
| Dialogue quality |
Are interviews generating detailed and relevant accounts? |
| Analysis strategy |
Does the study seek intensive case-level interpretation or comparisons across a broader sample? |
Information power offers a reasoned framework for planning and evaluating sample adequacy. It does not provide a universal formula or an automatically sufficient participant count.
Its usefulness is greatest when researchers can explain how these considerations operate in their actual study.
How Does Sample Specificity Affect Sample Size?
Sample specificity concerns how closely participants' experiences and characteristics align with the research question.
Suppose a study investigates how teachers develop performance-based assessments in fully online courses. Participants who have personally designed and implemented such assessments may provide more directly relevant accounts than teachers with only general familiarity with online education.
A highly specific sample can support focused analysis, but specificity should not be confused with homogeneity in every characteristic.
Researchers may still need variation in experience, disciplinary background, or institutional setting to investigate meaningful differences.
The important consideration is whether the sampling strategy provides the kinds of information necessary to address the research aim.
The relationship between sample specificity and qualitative sample size is therefore substantive rather than merely numerical.
Does Participant Diversity Require a Larger Sample?
It may, particularly when variation across participant groups is central to the research question.
For example, a study comparing experiences among students, teachers, and instructional designers may require sufficient representation of each perspective to support the intended analysis.
However, simply recruiting one participant from every imaginable category does not guarantee meaningful coverage.
Researchers should identify which differences are theoretically or contextually relevant and design sampling around those distinctions.
If detailed comparisons across several groups are essential, the required sample may be substantially larger than that for an intensive investigation of one relatively specific participant group.
How Does Interview Quality Influence Sample Adequacy?
The number of interviews is not equivalent to the amount of useful information collected.
An interview that produces detailed descriptions, concrete examples, and opportunities for clarification may contribute substantially more analytically useful material than a brief interview consisting largely of general statements.
Interview quality depends partly on question design, interviewer skill, rapport, participant familiarity with the phenomenon, and the conditions of data collection.
Nevertheless, rich interviews do not automatically compensate for missing perspectives or inadequate sampling coverage.
The quality of interviews and the number of participants needed should be considered jointly.
What Does Data Saturation Mean?
Data saturation is commonly used to describe a point at which additional data collection contributes insufficient new information for a specified analytical purpose.
However, saturation has several meanings. Researchers may distinguish the identification of new codes from the development of a richer understanding of themes or conceptual categories.
Hennink, Kaiser, and Marconi (2017), for example, distinguished code saturation from meaning saturation in qualitative interview research.
These forms of adequacy are not necessarily reached at the same point.
Researchers should therefore specify what saturation means in their study and how they intend to assess it.
Is Saturation Appropriate for Every Qualitative Study?
No. Saturation is closely associated with particular qualitative traditions and analytical approaches, but its assumptions are contested in others.
In reflexive thematic analysis, for example, themes are understood as actively developed through interpretive engagement rather than simply discovered as a finite inventory waiting to be exhausted.
For such an approach, claiming that no new themes can emerge may be inconsistent with its methodological assumptions.
Other approaches may evaluate adequacy through conceptual development, depth of interpretation, information power, or the completeness of a case account.
The decision about whether saturation fits the methodology should precede its use as a recruitment stopping rule.
What Does Existing Research Say About Qualitative Sample Sizes?
Methodological studies provide useful empirical observations about sample adequacy, but their findings should not be interpreted as universal recruitment prescriptions.
Guest, Bunce, and Johnson (2006) examined thematic saturation in a particular interview dataset. Hennink and Kaiser (2022) synthesized evidence on saturation across qualitative studies.
These publications help researchers understand conditions under which certain forms of saturation have been reported.
However, sample adequacy depends on the study population, research question, interview structure, analytical objective, and definition of saturation.
A number reported in one methodological study cannot automatically be transferred to a different qualitative design.
Can Previous Qualitative Studies Help Determine Sample Size?
Yes, provided their methodological relevance is assessed.
Previous studies may indicate the recruitment scale commonly used for a similar research aim, population, and analytical approach.
However, researchers should examine more than the final participant count. Relevant considerations include how participants were selected, the nature of the data, the scope of the analysis, and the authors' justification for adequacy.
For example, a study involving twelve highly focused interviews should not automatically justify twelve interviews in a broader comparative investigation.
Prior research can inform a provisional range, but it cannot establish adequacy without reference to the proposed study.
Should Researchers Specify a Sample Size Before Data Collection?
Usually, researchers need an initial recruitment plan for ethical review, resource allocation, scheduling, and methodological transparency.
This may take the form of a target number or a justified range, depending on the study design and institutional requirements.
For example, a researcher might provisionally plan fifteen to twenty interviews while specifying how ongoing analysis will inform whether additional recruitment is needed.
Such a range is a planning decision, not evidence that fifteen participants are necessarily insufficient or twenty necessarily sufficient.
The question of whether a thesis should predetermine a qualitative sample-size range depends partly on methodological flexibility and the requirements of the institution or ethics committee.
How Do You Develop an Initial Recruitment Range?
Begin with the research aim and the intended participant population.
Identify the types of experience or variation needed to address the question. Then consider the analytical approach, expected depth of each interview, and resources available for data collection and analysis.
Review methodologically comparable studies and relevant methodological literature to establish a plausible starting point.
Finally, define how sample adequacy will be reviewed during the study, where iterative recruitment is methodologically appropriate.
The resulting range should be presented as provisional and justified, not as a universal requirement derived from an arbitrary convention.
What Is the Difference Between Sampling Adequacy and Representativeness?
Qualitative purposive sampling commonly seeks participants who can provide relevant information rather than a statistically representative sample of a population.
A purposive sample can support detailed interpretation without allowing researchers to estimate population percentages or sampling margins of error.
However, the absence of a statistical representativeness objective does not justify arbitrary recruitment.
Researchers still need to explain the sampling logic, the boundaries of their claims, and the contexts to which their interpretations may be transferable.
Transferability requires sufficiently detailed contextual reporting so that readers can evaluate relevance to other settings.
How Do You Know When Recruitment Should Stop?
Recruitment should stop when the data are adequate for the specified research aim under the chosen methodology and analytical strategy, subject to ethical and practical constraints.
For studies using a defensible saturation criterion, this may involve monitoring whether additional interviews contribute new relevant codes, meanings, or conceptual relationships.
For studies emphasizing information power, researchers may evaluate whether the accumulated interviews provide sufficiently specific and rich material for the intended analysis.
For intensive case-based or interpretive approaches, the decision may depend on analytical depth and the completeness of the case account.
Researchers should document the rationale for stopping participant recruitment rather than simply state that the planned number was reached.
Can Too Many Participants Become a Problem?
Yes. More interviews may expand the range of perspectives, but they also increase the volume of material requiring careful interpretation.
When analytical time and resources are limited, excessive recruitment can reduce the attention devoted to each participant's account.
This concern is especially relevant to approaches requiring detailed idiographic or case-level analysis.
However, a larger sample is not inherently less rigorous. Its appropriateness depends on the research aim, analytical resources, and intended level of interpretation.
The possibility that too many qualitative participants may reduce analytical depth should be considered alongside the risks of inadequate coverage.
What If the Planned Sample Cannot Be Recruited?
Recruitment difficulties should prompt methodological reassessment rather than automatic acceptance of the achieved sample.
Researchers may need to reconsider recruitment channels, inclusion criteria, study scope, or the feasibility of particular subgroup comparisons.
However, changing eligibility criteria solely to increase participant numbers can undermine sample specificity and alter the phenomenon being investigated.
If the achieved sample provides insufficient information for the original research aim, the researcher may need to narrow the claims or revise the design transparently.
Ethics approval requirements should be considered before making material recruitment changes.
How Should Sample-Size Decisions Be Reported?
A qualitative methods section should explain the initial sampling strategy, eligibility criteria, anticipated or achieved participant numbers, and the rationale for adequacy.
If recruitment evolved during analysis, the report should describe the relevant decisions and why additional participants were or were not sought.
Researchers should avoid unsupported statements such as "twelve participants were sufficient because qualitative research requires only a small sample."
Likewise, claiming saturation without explaining its meaning or assessment procedure provides limited methodological transparency.
Vasileiou and colleagues (2018) documented shortcomings in how qualitative interview sample sizes were characterized and justified in published studies, reinforcing the importance of explicit reasoning.
