Should You Explain Why Certain Variables or Populations Were Excluded?

Is It Enough to Say That a Population or Variable Was “Outside the Scope”?

You decide to study first-year students but not students in later year levels. You examine self-efficacy but not academic performance. You exclude a particular participant group, omit a plausible variable, or restrict the study to one setting.

Do you need to explain every one of those decisions?

Not necessarily. Every study excludes far more possibilities than it includes, and a manuscript would become unreadable if researchers attempted to justify every imaginable population, variable, setting, period, or method they did not investigate.

Some exclusions, however, are consequential. Readers may reasonably expect a particular population or variable to be included, the exclusion may affect how the evidence should be interpreted, or the decision may be important for evaluating bias and applicability.

In those situations, simply writing that something was "outside the scope" tells the reader where you drew the boundary but not why. Important exclusions should be explained when their rationale or consequences matter to understanding the design, evaluating the evidence, or interpreting the conclusions.

Explain Exclusions That Matter to the Question, Design, or Interpretation

A Useful Explanation Tells Readers Why the Boundary Exists and Why It Matters

Research boundaries need different levels of explanation

Every research question establishes boundaries. A study of first-year university students excludes children, postgraduate students, faculty members, employees, retirees, and countless other populations. A study of writing self-efficacy excludes innumerable other constructs that could theoretically be measured.

Most of those exclusions do not need individual explanations because the research question already makes their irrelevance reasonably clear.

The need for explanation increases when an exclusion is less obvious or more consequential. A knowledgeable reader might reasonably ask why a relevant population was omitted, why an important variable was not measured or analyzed, or why a group that initially appeared eligible was excluded.

A useful principle is therefore proportionality: the more an exclusion could affect the study's validity, interpretation, applicability, or conceptual completeness, the more clearly its rationale should be reported.

Explain an exclusion when readers would reasonably expect inclusion

Suppose you investigate generative AI use among undergraduate students but include only first-year students. If the research question specifically concerns transition into university, the rationale may be obvious and easily stated.

If the question instead refers broadly to "undergraduate students," readers may reasonably wonder why later-year students were absent.

The same applies to variables. If a study examines academic achievement and previous literature consistently identifies prior achievement as important to the intended analysis, omitting it may require explanation. By contrast, researchers generally do not need to explain why they failed to measure every conceivable correlate of academic performance.

Ask whether a knowledgeable reader familiar with the research problem would stop at the boundary and ask, "Why did you leave that out?" If the question is predictable and methodologically relevant, answer it in the manuscript rather than leaving readers to infer the rationale.

Explain population exclusions because they define who contributes evidence

In participant-based studies, eligibility decisions directly determine the study population. Inclusion criteria describe key characteristics of the target population used to answer the research question. Exclusion criteria concern additional characteristics of otherwise potentially eligible participants that may interfere with study participation, introduce particular problems for the research, or increase risk in intervention studies.

Methodological guidance emphasizes that researchers should not only establish appropriate inclusion and exclusion criteria but also consider how those choices affect external validity. If people with a particular characteristic are excluded, the resulting evidence may not support the same conclusions for that excluded group.

This is why reporting the population boundary matters. Readers need enough information to understand who could participate, who could not, and what population the resulting evidence represents.

Do not confuse defining the population with listing its opposite as an exclusion

A common mistake is to duplicate the same characteristic across inclusion and exclusion criteria.

If your study population is explicitly defined as first-year undergraduate students, you do not normally improve methodological clarity by adding "second-, third-, and fourth-year students are excluded" as three separate exclusion criteria. The positive population definition already establishes that boundary.

This distinction prevents the eligibility section from becoming a catalogue of everyone outside the target population. Published methodological guidance specifically identifies using the same variable to define both inclusion and exclusion criteria as a common error.

Explain population exclusions when they affect applicability

A population exclusion can be methodologically defensible while still affecting the range of people represented by the findings.

Suppose an intervention study excludes participants with a particular comorbidity because that condition could interfere with the intervention or create additional risk. The rationale may be sound. Yet the study will provide less direct evidence about whether the findings apply to people with that comorbidity.

That consequence should not be hidden simply because the exclusion was justified.

Methodological guidance on eligibility criteria explicitly connects inclusion and exclusion decisions to external validity. Researchers should consider whether characteristics of the resulting sample limit the populations to which the results can reasonably be generalized.

A useful explanation can therefore distinguish two questions:

Answering the first question does not make the second disappear.

Explain exclusions that could create or reduce bias

Some eligibility decisions matter not only for applicability but also for the internal interpretation of the study.

Researchers may exclude participants because a particular condition could interfere with measurement, create a competing explanation, prevent completion of required procedures, or otherwise compromise the intended design. In such cases, readers need enough rationale to understand why the criterion improves the study.

Conversely, exclusion itself can sometimes create selection-related problems. Removing particular participants or observations may systematically change the evidence being analyzed.

This becomes especially important when exclusions are introduced after researchers have seen the data or results. A transparent explanation allows readers to evaluate whether the decision follows a defensible criterion or appears driven by the effect it has on the findings.

Variable exclusions require a different kind of explanation

Populations and variables are both elements of research scope, but excluding them creates different methodological questions.

For a population, you usually ask who contributes evidence and whom the resulting evidence represents.

For a variable, you ask what role that construct would have played in the conceptual or analytical model and whether its absence affects the interpretation you intend to make.

Suppose your study examines the relationship between generative AI use and writing self-efficacy. You do not need to explain why you failed to include every construct associated with learning. Motivation, creativity, anxiety, digital literacy, academic performance, and technology acceptance do not automatically belong in the study simply because they are related to education or AI.

But if previous evidence and your causal assumptions indicate that prior writing achievement is an important confounder for the relationship you intend to estimate, omitting it is more consequential. Readers may need to know why it was not measured or adjusted for and what that omission means for interpretation.

Do not justify variable selection solely with statistical significance

One weak explanation is that a variable was excluded because it was "not significant."

Whether a variable belongs in an analysis depends on the purpose of the model and the role of that variable, not simply on whether its individual p-value crosses a conventional threshold. In causal analyses, for example, confounder selection should reflect substantive and causal reasoning. In predictive research, variable-selection considerations differ. Descriptive analyses have different aims again.

The appropriate rationale therefore depends on what the analysis is designed to accomplish.

If a variable was planned but later omitted because it could not be measured reliably, had extensive missing data, was unavailable in the dataset, or proved conceptually inappropriate, report the actual reason and consider the implications rather than retrofitting a more flattering explanation.

“Outside the scope” describes a decision but does not justify it

Researchers often write statements such as:

"Academic performance was excluded because it was outside the scope of the study."

This is circular. The variable is outside the scope because the researcher excluded it, and it was excluded because it is outside the scope. Nothing has been explained.

A stronger rationale connects the boundary to the purpose of the research:

"The study examines students' perceived capability for academic writing rather than objective writing performance; academic performance outcomes therefore fall outside the construct addressed by the research question."

The second statement tells readers why the boundary exists.

The same principle applies to populations. "Postgraduate students were outside the scope" provides less information than explaining that the study concerns students' transition into undergraduate university study and therefore focuses on first-year undergraduates.

Feasibility is a legitimate reason, but it changes what you can claim

Researchers operate within real constraints. Access, time, funding, personnel, data availability, equipment, and expertise can affect what can realistically be studied.

It is acceptable for feasibility to influence scope. What matters is whether the resulting research question and claims are aligned with the narrower evidence.

Suppose a researcher originally intends to study students from five universities but ultimately has authorized access to only one. If the project is redesigned as a single-institution study, that narrower scope can be reported honestly and justified according to the revised research purpose.

What would be misleading is retaining a question about university students generally while presenting the absence of the other institutions as though it has no implications.

If available evidence forces the study to change, the issue may extend beyond explaining an exclusion to reconsidering the scope itself in light of the data available.

Ethical and safety exclusions should state the relevant reason

Some participant exclusions exist because participation could create unacceptable risk or because the procedures are unsuitable for particular individuals. In intervention research, safety-related eligibility criteria are common.

When such criteria are used, explain the study-specific risk or methodological reason at the appropriate level of detail. Avoid implying that a population is inherently unsuitable for research when the actual issue concerns the particular intervention or procedure.

Researchers should also avoid unnecessary exclusion of groups that could participate with appropriate safeguards or accommodations. Ethical justification involves more than invoking "participant safety" as a generic phrase.

Explain exclusions prospectively whenever possible

Major population and analytical boundaries are easier to defend when they are established during study design rather than after results become visible.

Prospective criteria show that the boundary follows the research question, protocol, ethics requirements, or analytical strategy rather than the direction of the findings.

This does not mean criteria can never change. Recruitment difficulties, new information, measurement failures, unavailable data, or other circumstances may require revision. When that happens, transparency becomes more important.

State what changed, why it changed, and when appropriate how the change affects interpretation.

Do not rewrite the history of the project so that an unplanned exclusion appears to have been an elegant methodological decision all along. Peer reviewers have seen that movie before.

Not every excluded variable deserves a paragraph

Transparency should not become an inventory of everything you did not study.

Suppose your research concerns the relationship between students' AI-assisted writing practices and writing self-efficacy. You generally do not need separate paragraphs explaining why the study excludes physical activity, commuting distance, dietary habits, music preferences, and every other characteristic absent from the conceptual model.

The exclusions worth discussing are those that meet one or more of these conditions:

• the element is closely connected to the research question;
• readers would reasonably expect it to be included;
• its absence affects the intended analysis or interpretation;
• its exclusion could influence bias or applicability;
• the decision changed from the original plan;
• the exclusion requires ethical or methodological justification.

Otherwise, defining what the study includes is usually sufficient.

The rationale belongs where readers need it

There is no universal section in which every exclusion must be explained. Reporting conventions vary by discipline, methodology, institution, thesis format, and journal.

Major deliberate boundaries may appear when the scope and delimitations are defined. Participant eligibility criteria generally belong in the methods. Analytical exclusions should be reported with the relevant analytical procedures. Consequences discovered or recognized when interpreting findings may need discussion as limitations.

The same boundary can occasionally require mention in more than one place because each section serves a different purpose. Avoid simply duplicating the same sentence. Explain the aspect relevant to that part of the report.

Justification and acknowledgment are different tasks

A particularly important distinction is between explaining why an exclusion was reasonable and acknowledging what the study loses because of it.

Suppose researchers restrict participation to first-year students because the phenomenon concerns transition into university. That is the justification.

The researchers may still acknowledge that the findings do not directly establish whether the same patterns occur among students in later years. That is a consequence of the boundary.

Both statements can be true simultaneously.

A well-justified delimitation is not a magical generalizability permit. Nor does acknowledging a consequence mean that the original decision was a methodological mistake.

This distinction follows from the broader difference among scope, delimitations, and limitations.

Your explanation should be proportional to how consequential the exclusion is

A useful reporting principle is to give important decisions enough explanation for readers to evaluate them without allowing peripheral decisions to overwhelm the article.

This proportional approach provides transparency without turning the manuscript into a defensive autobiography of every decision the researcher ever considered.

From “Outside the Scope” to a Methodologically Useful Explanation

The improved explanations are not necessarily much longer. Their advantage is that they reveal the logic of the study rather than merely announcing its boundaries.

Common Mistakes When Explaining Research Exclusions

Explain Enough for a Reader to Reconstruct the Logic of the Boundary

For each important exclusion, ask whether readers need to know only that the boundary exists or whether they also need its rationale and consequences.

If you cannot provide a convincing explanation for a consequential exclusion, the problem may not be the writing. Reconsider whether the population or variable can actually be excluded on methodological grounds.

If you find yourself writing explanations for dozens of exclusions, return to the more fundamental question of what genuinely needs to be left outside this particular study. A coherent scope should do much of the explanatory work for you.

Does This Exclusion Need an Explanation?

Frequently Asked Questions About Explaining Research Exclusions

Explain the Boundary When Understanding Its Logic Matters

How to Cite This Guide

This guide is intended to be read, shared, and used in research, teaching, and academic work. If you draw on its ideas, explanations, or other content, please acknowledge the source by citing the guide. Doing so gives appropriate credit and helps your readers locate the original resource.