>

>

How to Choose a Sample Size for a Student Study

How to Choose a Sample Size for a Student Study

Princeton Journal of Pre-Collegiate Research

A high school student reviewing statistical charts and sample size calculations for an original research study

Among the most consequential methodological decisions a student researcher must make is determining how to choose a sample size for a student study. Sample size selection directly governs the statistical power of a study, the reliability of its conclusions, and the degree to which findings may be generalized to broader populations. Insufficient sample sizes produce underpowered analyses in which genuine effects fail to reach statistical significance, while excessively large samples may introduce logistical burdens that are incompatible with the resource constraints typical of pre-collegiate research environments. A principled, systematic approach to sample size determination is therefore essential for any student seeking to conduct original, peer-reviewed research of publishable quality.

The Princeton Journal of Pre-Collegiate Research publishes original, peer-reviewed research by high school students across the sciences, social sciences, humanities, and interdisciplinary fields, and the methodological rigor of submitted manuscripts is evaluated with particular attention to the appropriateness of sampling decisions. Reviewers routinely assess whether the chosen sample size is justified through formal power analysis or, at minimum, through explicit reference to disciplinary conventions and prior literature. Students who wish to understand what reviewers look for in a student manuscript will find that sample size justification ranks among the most frequently cited areas requiring revision in otherwise competent submissions.

Foundational Concepts Underlying Sample Size Determination

Before a student can determine an appropriate sample size, it is necessary to understand the statistical concepts that govern the relationship between sample size and inferential validity. Three parameters are central to this determination: statistical power, effect size, and significance threshold (alpha level).

Statistical power, conventionally denoted as 1 minus beta, represents the probability that a study will correctly detect a true effect when one exists. A power of 0.80 is widely accepted as the minimum acceptable threshold in the behavioral and biological sciences, indicating an 80 percent probability of detecting a true effect of a specified magnitude. Effect size quantifies the magnitude of the phenomenon under investigation and is typically expressed through standardized metrics such as Cohen's d for comparisons of means, Pearson's r for correlational analyses, or eta-squared for analyses of variance. The significance threshold, or alpha, defines the probability of incorrectly rejecting a true null hypothesis and is most commonly set at 0.05 in student research contexts.

These three parameters are mathematically interrelated: for a fixed alpha and effect size, increasing the desired power requires a larger sample, while studies anticipating larger effect sizes require smaller samples to achieve equivalent power. Students must therefore make explicit assumptions about each parameter prior to computing a required sample size, and those assumptions must be grounded in prior empirical literature rather than selected arbitrarily.

How to Choose a Sample Size for a Student Study Using Formal Power Analysis

Formal a priori power analysis represents the gold standard for sample size justification in quantitative research. In this approach, the researcher specifies the anticipated effect size, the desired power level, and the chosen alpha level, and then solves for the minimum sample size required to satisfy those constraints. Numerous freely available computational tools, including G*Power and the pwr package in R, facilitate this calculation for a wide range of statistical tests including t-tests, chi-square tests, ANOVA, and linear regression.

To illustrate the process, consider a student investigating whether a structured peer-tutoring intervention produces measurable improvements in algebra assessment scores relative to a control condition. If prior literature on comparable interventions reports a medium effect size of Cohen's d equal to 0.50, a student targeting 80 percent power at alpha equal to 0.05 using an independent-samples t-test would require approximately 64 participants per group, yielding a total sample of 128. If the anticipated effect size were smaller, for example d equal to 0.30, the required sample would increase to approximately 176 per group, a figure that may exceed the practical capacity of a single-school study.

When prior literature is sparse or the research question is genuinely novel, students may conduct a pilot study with a small convenience sample of 10 to 20 participants to generate preliminary effect size estimates, which are then used to inform the power analysis for the full study. This two-stage approach is methodologically defensible and is explicitly acknowledged in the peer review standards applied to pre-collegiate submissions. For additional guidance on the computational procedures involved, students are encouraged to consult the detailed resource on calculating sample size for a student research study, which provides worked examples across multiple research designs.

Discipline-Specific Conventions and Their Implications for Sample Size

Sample size norms vary substantially across research disciplines, and students must situate their sampling decisions within the conventions of the field in which their study is located. In experimental psychology and educational research, sample sizes of 30 to 200 participants per condition are common, with the precise requirement depending on the expected effect magnitude and the number of predictors or factors in the design. In clinical and epidemiological research, larger samples are typically required due to the expectation of smaller effect sizes and the need to control for multiple confounding variables.

In the biological sciences, sample size requirements are often determined by the unit of analysis. Studies examining gene expression in cell cultures may require as few as three to six biological replicates per condition if the anticipated effect is large and measurement error is low, whereas ecological surveys of species abundance may require sampling across dozens of sites to achieve adequate spatial representativeness. Chemistry and materials science studies frequently rely on replicate measurements rather than independent subjects, and the number of replicates required is governed by the coefficient of variation of the measurement instrument rather than by population-level power considerations.

Social science and survey-based studies introduce additional complexity, as the required sample size is influenced not only by statistical power but also by the desired margin of error for descriptive estimates. For a simple proportion estimated from a random sample, the standard formula yields a required sample of approximately 385 for a margin of error of five percentage points at 95 percent confidence, assuming maximum variance. Students conducting survey research should apply this formula explicitly and report the resulting margin of error alongside their findings.

Practical Constraints and Their Methodological Implications

Pre-collegiate researchers operate under resource constraints that frequently preclude the attainment of ideally powered samples. Limited access to participants, restricted laboratory time, budgetary limitations, and institutional review board considerations may collectively constrain the maximum achievable sample size. When such constraints are operative, students are advised to adopt one or more of the following methodological strategies to preserve the inferential value of their research.

  • Within-subjects designs: Experimental designs in which each participant serves as their own control substantially reduce the required sample size relative to between-subjects designs, because individual differences are statistically controlled. For a within-subjects comparison with an anticipated effect of Cohen's d equal to 0.50 and 80 percent power at alpha equal to 0.05, the required sample is approximately 34 participants rather than 64 per group.

  • Replication of established paradigms: Studies that replicate previously published findings with minor modifications benefit from well-characterized effect size estimates, enabling precise power calculations and reducing uncertainty about the required sample. Students considering this approach should consult the discussion of replication studies and their suitability for student researchers to assess whether this design aligns with their research objectives.

  • Transparent reporting of limitations: When the achieved sample falls below the ideally powered threshold, students must explicitly acknowledge this limitation in the discussion section of their manuscript, quantify the resulting reduction in power, and constrain their conclusions accordingly. Underpowered studies that are transparently reported and appropriately qualified retain scientific value as contributions to the cumulative evidence base.

  • Longitudinal designs: In some contexts, repeated measurement of a smaller sample over time can yield richer data than a single cross-sectional assessment of a larger sample. Students exploring this option should review the methodological considerations involved in conducting a longitudinal study as a student researcher before committing to this design.

How to Choose a Sample Size for a Student Study Across Different Research Contexts

The appropriate procedure for sample size determination differs according to the methodological paradigm of the study. Quantitative experimental and quasi-experimental studies should employ a priori power analysis as described above. Quantitative observational studies, including cross-sectional surveys and correlational analyses, should apply the relevant formula for the primary inferential test while also considering the margin of error for descriptive estimates. Qualitative studies, including interview-based and ethnographic designs, do not employ statistical power analysis; instead, sample size is governed by the principle of theoretical saturation, which holds that data collection should continue until no new conceptual categories emerge from the data. A sample of 12 to 25 semi-structured interviews is commonly sufficient to reach saturation in homogeneous populations, though this figure varies with the complexity and heterogeneity of the phenomenon under study.

Mixed-methods studies present the most complex sampling challenge, as the quantitative and qualitative components may each require distinct sampling rationales. In such designs, the quantitative component should be powered according to the primary statistical test, while the qualitative component should be sized according to saturation principles. The two samples need not be drawn from the same participants, and students should clearly distinguish the sampling logic governing each strand of the study in their methods section.

Reporting Sample Size Decisions in a Student Manuscript

Transparent and complete reporting of sample size decisions is a non-negotiable requirement for manuscripts submitted to peer-reviewed student journals. The methods section should include, at minimum, the following elements: the target sample size, the statistical test for which the power analysis was conducted, the anticipated effect size and its empirical basis, the desired power level, the alpha level, and the software or formula used to compute the required sample. If the achieved sample differs from the target, the discrepancy should be explained and its implications for statistical power should be quantified.

Students preparing manuscripts for submission should also be aware that sample size reporting conventions vary across journals and disciplines. Journals indexed in the biological and medical sciences frequently require adherence to reporting guidelines such as CONSORT for randomized trials or STROBE for observational studies, both of which include explicit sample size reporting items. Pre-collegiate journals such as the Princeton Journal of Pre-Collegiate Research evaluate submissions against the methodological standards of the relevant discipline, and reviewers are instructed to assess whether sample size justification is adequate and whether the reported statistics are consistent with the stated sample.

Students who are in the early stages of designing their research and have not yet determined an appropriate sample size are encouraged to begin by reviewing the foundational guidance available through the high school student research getting started resource, which provides a structured overview of the research design process from question formulation through data collection planning. Additionally, students at various stages of the publication process, including those based in international contexts, may find relevant guidance through country-specific publishing resources such as those addressing publishing research as a high school student in Germany or publishing research as a high school student in Brazil, each of which addresses the intersection of local academic conventions and international publishing standards.

Selecting an Appropriate Journal After Sample Size Decisions Are Finalized

Once the research design is finalized and data collection is complete, students must identify a publication venue whose scope and methodological standards are aligned with the study's design and sample characteristics. Journals that specialize in pre-collegiate research evaluate submissions with awareness of the practical constraints under which student researchers operate, and they apply review criteria that are calibrated accordingly. However, this accommodation does not extend to the absence of sample size justification; even journals with a developmental mission expect students to demonstrate that sampling decisions were made deliberately and with reference to established statistical principles.

Students who are uncertain about which publication venue is appropriate for their work should consult the comprehensive overview of student journals and how to choose among them, which provides evaluative criteria for assessing journal quality, scope alignment, and peer review rigor. Selecting a journal whose standards match the methodological sophistication of the submitted manuscript is as important as any other element of the publication process, and students are advised to conduct this evaluation systematically rather than defaulting to the most prominent or most accessible venue.

In summary, the question of how to choose a sample size for a student study admits no single universal answer; the appropriate sample size is a function of the research design, the anticipated effect magnitude, the desired inferential power, and the practical constraints of the research environment. Students who approach this decision systematically, grounding their choices in formal power analysis or disciplinary convention and reporting those choices transparently in their manuscripts, will substantially enhance the scientific credibility and publishability of their research.

Have questions or want personalised guidance? Contact us and we'll be happy to help.

Read More

Diagram illustrating axion particle detection apparatus used in dark matter research experiments

Axions and the Search for Dark Matter, Explained for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Conceptual diagram of axion dark matter detection apparatus with magnetic field coils and microwave cavity resonator for student research

Axions and dark matter: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Conceptual illustration of axion particles and dark matter distribution in a galactic halo, relevant to particle physics and cosmology research

Axions and dark matter: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram illustrating the distance from the Sun to Earth and Mars with labeled orbital paths in the solar system

Distance From the Sun to Earth (and Mars): Solar System Distances Explained

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram showing scaled distances between planets in the solar system for student research and educational experiments

Distances in the solar system: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram illustrating the relative distances between planets in the solar system, with scale markers in astronomical units

Distances in the solar system: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

False-color map of Mars crustal magnetic field anomalies detected by the Mars Global Surveyor magnetometer, showing striped magnetic signatures in the southern highlands

Does Mars Have a Magnetic Field? What We Know and How We Know

By

Princeton Journal of Pre-Collegiate Research

Read more

The Martian magnetic field: 10 Research Questions and Experiment Ideas for Students

The Martian magnetic field: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Illustration of Mars with crustal magnetic field lines and solar wind interaction depicted in scientific diagram style

The Martian magnetic field: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram illustrating rolling friction forces acting on a wheel in contact with a flat surface, with labeled vectors for normal force and resistive torque

Rolling Friction Explained: Definition, Examples and Experiments for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

High school student measuring rolling friction of a cylinder on an inclined plane in a physics laboratory setting

Rolling friction: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram illustrating rolling friction forces acting on a sphere rolling across a flat surface, with labeled vectors for normal force, friction, and deformation

Rolling friction: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

High school student conducting a controlled friction experiment on an inclined plane with a wooden block and spring scale

How to Find the Coefficient of Kinetic Friction: A Student Experiment Guide

By

Princeton Journal of Pre-Collegiate Research

Read more

High school student measuring the coefficient of kinetic friction using a wooden block and spring scale on an inclined plane in a laboratory setting

The coefficient of kinetic friction: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

The coefficient of kinetic friction: 12 Questions Students Ask, Answered

The coefficient of kinetic friction: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram of standing wave harmonics on a vibrating string showing nodes and antinodes at fundamental and overtone frequencies

Harmonics and Standing Waves: What They Are and How to Test Them

By

Princeton Journal of Pre-Collegiate Research

Read more

High school student conducting a standing wave experiment with a vibrating string apparatus in a physics laboratory

Harmonics and standing waves: 10 Research Questions and Experiment Ideas for Students

By

Princeton Journal of Pre-Collegiate Research

Read more

Diagram illustrating harmonic frequencies and standing wave nodes and antinodes on a vibrating string in a physics laboratory setting

Harmonics and standing waves: 12 Questions Students Ask, Answered

By

Princeton Journal of Pre-Collegiate Research

Read more

Mathematical proof of the AM-GM inequality written on a chalkboard with algebraic notation and inequality symbols

AM-GM Inequality: Proof, Examples and Olympiad Uses

By

Princeton Journal of Pre-Collegiate Research

Read more

Educator reviewing a student research manuscript in an academic setting with scientific journals and data charts on the desk

For Educators: Supporting Student Research and Publication

By

Princeton Journal of Pre-Collegiate Research

Read more

A high school teacher reviewing a student's research manuscript at a desk covered with scientific papers and reference materials

How Teachers Can Support a Student’s First Publication

By

Princeton Journal of Pre-Collegiate Research

Read more

Princeton, New Jersey, United States
Published and Managed by The Princeton Journal of Precollegiate Scholarship Inc.
ISSN: 3143-8423
DOI: 10.67698

Copyright © Princeton Journal of Pre-Collegiate Research. All rights reserved

PJPCR is independently operated and is not affiliated with Princeton University or any of its colleges, departments or programs.

Princeton, New Jersey, United States
Published and Managed by The Princeton Journal of Precollegiate Scholarship Inc.
ISSN: 3143-8423
DOI: 10.67698

Copyright © Princeton Journal of Pre-Collegiate Research. All rights reserved

PJPCR is independently operated and is not affiliated with Princeton University or any of its colleges, departments or programs.

Princeton, New Jersey, United States
Published and Managed by The Princeton Journal of Precollegiate Scholarship Inc.
ISSN: 3143-8423
DOI: 10.67698

Copyright © Princeton Journal of Pre-Collegiate Research. All rights reserved

PJPCR is independently operated and is not affiliated with Princeton University or any of its colleges, departments or programs.