How to Determine the Population, Sample, and Sampling Method?

What Is a Population?

The population is the full set of individuals, institutions, events, objects, or other units to which the study seeks to relate its findings.

Target and Accessible Populations

• Target population: the wider group to which results are theoretically intended to apply.
• Accessible population: the group the researcher can realistically reach within time, institutional, geographic, and access constraints.

What Is a Sample?

A sample is the group of individuals or units actually included in the study. In quantitative research it is often used to make inferences about a population; in qualitative research it may be selected for depth and relevance of experience.

Probability Sampling

In probability sampling, the probability of selection is known or calculable. When properly implemented, it provides a stronger basis for statistical generalisation.

Simple Random Sampling

Each unit has an equal or known probability of selection. This usually requires an appropriate sampling frame.

Systematic Sampling

Units are selected at regular intervals after a starting point. Periodic patterns in the list can create bias.

Stratified Sampling

The population is divided into meaningful strata, such as sex, profession, institution type, region, or education level, and participants are selected from each stratum.

Cluster and Multistage Sampling

Cluster sampling selects natural groups such as schools or institutions. Multistage sampling combines several selection stages, for example region → city → institution → participant.

Non-Probability Sampling

In non-probability sampling, selection probabilities are unknown. These approaches are common in exploratory and qualitative research and require caution when generalising to a wider population.

Convenience Sampling

Participants are selected because they are easy to access. This is practical but vulnerable to selection bias.

Purposive and Criterion Sampling

Purposive sampling selects information-rich participants or cases. Criterion sampling includes only those who meet predefined conditions relevant to the research question.

Maximum Variation, Typical, and Extreme Cases

These strategies seek diversity, typicality, or unusually informative cases depending on the study purpose.

Snowball, Quota, and Volunteer Sampling

Snowball sampling recruits through participant networks; quota sampling fills predetermined subgroup targets; volunteer sampling relies on self-selection. Each carries its own bias risks.

Sampling in Qualitative Research

Qualitative sampling aims for relevance and richness rather than statistical representation. Sample adequacy depends on the question, design, participant specificity, data richness, analytic approach, saturation, or information power.

Saturation and Information Power

Saturation: the point at which new data no longer add meaningfully new themes, categories, or explanations.

Information power: a narrower aim, more specific sample, and richer data may justify a smaller sample.

Sampling by Qualitative Design

Phenomenology: select participants who have directly experienced the phenomenon.

Grounded theory: purposive sampling may be followed by theoretical sampling as categories develop.

Case study: the selected unit may be an institution, programme, event, team, or process rather than an individual.

Mixed methods: quantitative and qualitative components may use different strategies; their relationship should be explained.

Eligibility Criteria and Sampling Frame

Inclusion criteria define who may enter the study.

Exclusion criteria define scientifically justified reasons for excluding otherwise eligible units.

Sampling frame is the accessible list from which the sample is selected.

Sampling Bias and Nonresponse Bias

Sampling bias occurs when some units are systematically more likely to be included than others.

Nonresponse bias arises when participants and nonparticipants differ systematically. Report invitations, participation, and response rates where appropriate.

Representativeness

Representativeness depends on more than sample size. Consider the sampling method, quality of the frame, response rate, subgroup distribution, similarity to the population, and missing data.

Sample Size Is Not Sampling Method

Sample size concerns how many units are included; sampling method concerns how they are selected. A large sample does not automatically correct a weak sampling design.

How to Report Sampling

• Target or accessible population
• Population size, where known
• Sampling method
• How sample size was determined
• Inclusion criteria
• Exclusion criteria
• Recruitment procedure
• Final analytic sample

Common Mistakes

• Confusing population and sample
• Calling an accessible sample random without random selection
• Describing a volunteer online survey as simple random sampling
• Failing to report the sampling method
• Not explaining how sample size was determined
• Creating eligibility criteria after seeing the data
• Overgeneralising from non-probability samples
• Justifying qualitative sample size only by a numerical rule
• Claiming saturation without explaining how it was assessed
• Assuming a large sample is automatically representative

Before Submission, Check

• Is the target population clearly defined?
• Are target and accessible populations distinguished where necessary?
• Is the sample clearly described?
• Is the sampling method named correctly?
• Is the rationale for the sampling method explained?
• Are inclusion and exclusion criteria reported?
• Is sample-size determination explained?
• Is the final analytic sample reported?
• Are implications for generalisability considered?
• Is qualitative sample adequacy justified in a design-appropriate way?