Can a Scope Be Too Broad Even When the Sample Size and Resources Are Adequate?

If You Have the Resources, Why Not Study More?

Advice to narrow a research study is often framed as a feasibility issue. You have limited time, a limited budget, a limited number of participants, or only so much data, so you reduce the scope until the project becomes manageable.

But suppose those constraints are not particularly restrictive. You have a large dataset, sufficient participants, capable collaborators, adequate funding, and enough time. Can the study still be too broad?

Yes. Feasibility is only one test of an appropriate scope. A study can be entirely possible to conduct while still trying to answer too many conceptually distinct questions, combining phenomena that require different explanations, or producing a collection of analyses without a sufficiently coherent intellectual center.

Feasible Does Not Automatically Mean Coherent

Resources Determine What You Can Do, Not Everything You Should Do

Feasibility Is Only One Criterion for a Good Research Question

Research-question frameworks such as FINER explicitly distinguish feasibility from other considerations, including whether a question is interesting, novel, ethical, and relevant. Feasibility itself may involve sample availability, expertise, time, funding, data, and manageable scope. Passing that test tells you that a project can realistically be conducted. It does not establish that every possible addition will improve the study.

A well-resourced research team can therefore design a study that is feasible but intellectually overextended. The ability to collect twenty variables does not establish that all twenty variables belong in the same argument. Access to several populations does not mean every population needs to be compared. A large sample does not require you to answer every question the dataset makes statistically possible.

A Broad Scope Becomes Problematic When the Study Loses Its Center

A study may legitimately contain several research questions. Multiple outcomes, predictors, groups, or methods are not inherently signs of excessive scope. The more useful test is whether those elements contribute to a shared explanatory, descriptive, evaluative, or theoretical purpose.

Imagine a study of generative AI in higher education that examines student achievement, academic integrity, teacher workload, institutional policy, student mental health, employability, assessment redesign, and faculty professional development across several countries. With a large international consortium, the project may be technically achievable.

Yet feasibility does not tell you whether those questions constitute one study. Some may require different theoretical frameworks, units of analysis, participants, measures, and forms of evidence. At some point, the project may be better understood as a research program containing several related studies.

Count Distinct Inferential Tasks, Not Just Variables

Researchers sometimes judge breadth by counting variables. That can be misleading. Ten measures used to examine one well-defined construct may create less conceptual breadth than three variables used to answer three unrelated questions.

Instead, identify the distinct inferential tasks in the project. Are you estimating an intervention effect? Explaining why the effect occurs? Comparing implementation across institutions? Examining participants' experiences? Evaluating policy consequences? Predicting future behavior?

These questions may be connected, and some designs can appropriately address several of them. But each additional inferential task may require its own rationale, evidence, assumptions, analytical strategy, and interpretation. A project becomes increasingly difficult to defend as one coherent study when those tasks share little beyond the general topic.

More Research Questions Can Create Competing Priorities

One sign of excessive breadth is that the study no longer has a clear primary question. Every objective appears equally important, yet different objectives pull the design in different directions.

For example, a sample optimized for estimating an overall effect may not be ideal for detailed subgroup comparisons. Data collection designed for a quantitative outcome may provide little insight into implementation processes. A short observation period may suit one outcome while being inadequate for another.

Even when you have enough resources to accommodate all of these elements, the resulting design may become difficult to explain because there is no obvious basis for deciding which methodological requirement should take priority.

Broad Scope Can Increase Analytical Complexity Without Increasing Contribution

A larger dataset creates analytical possibilities, but possibilities are not the same as research questions. Adding outcomes, subgroups, predictors, interactions, and exploratory comparisons can generate an enormous number of analyses.

In quantitative studies, multiple planned comparisons can have statistical consequences and should be considered in the design and analysis. More generally, extensive analytical flexibility can make it harder to distinguish primary analyses from secondary or exploratory ones.

The practical question is therefore not, "How much can this dataset support?" but, "Which analyses are necessary to answer the questions this study was designed to address?"

Methodological Diversity Is Not the Same as Scope Creep

A mixed-methods study may use interviews, surveys, observations, and administrative data while remaining tightly focused if those sources address complementary dimensions of the same research problem. Conversely, a study using only one survey can be too broad if it attempts to answer a dozen loosely connected questions.

Method count is therefore a poor proxy for scope. What matters is the relationship among the components and whether each contributes to the study's intended inference or explanation.

Large Projects Often Need a Programmatic Structure

Sometimes broad inquiry is appropriate, but the organizational unit should change. A funded project might contain several work packages. A longitudinal dataset might support several papers. A dissertation may contain related empirical studies. A research consortium may investigate several connected questions under one overarching program.

Recognizing this structure can improve rather than diminish the research. Instead of forcing every question into one omnibus study, researchers can identify which questions genuinely belong together and which deserve separate designs or analyses. This is particularly useful when an expanding scope begins to represent several studies.

The Strongest Test Is Whether Every Major Component Serves the Same Intellectual Purpose

Take each research question, objective, population, construct, and major analysis and ask what would happen if it were removed. Would the central argument become incomplete? Would an essential part of the main question become unanswerable? Or would the study simply contain one fewer interesting analysis?

If many components fall into the last category, the project may be accumulating opportunities rather than defining a coherent scope.

This does not mean those questions should be abandoned. They may deserve separate studies, secondary analyses, or later projects. Preventing scope creep during the project often depends on distinguishing a worthwhile future question from a necessary current one.

When a Large Dataset Makes Too Many Studies Possible

Common Misconceptions About Broad, Well-Resourced Studies

Test Coherence Separately From Feasibility

Once you know that the project is feasible, conduct a second scope assessment that temporarily ignores your budget, sample size, and staffing. Ask whether the intellectual architecture still makes sense.

Resources should help you answer an important question well. They should not pressure you into maximizing the number of questions merely because you can.

Check Whether a Feasible Study Is Still Too Broad

Questions About Broad Research Scope and Adequate Resources

Having the Capacity to Study More Does Not Mean One Study Should Contain More

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.