Search across guide titles, topics, keywords, and content throughout the Researcher's Field Guide.
Showing 801–825 of 2,119 results
Establishing whether an outcome occurred is not the same as explaining why it occurred. Learn how these questions differ, what evidence each requires, and when a research design can support both conclusions.
Read Guide →Collecting relevant data does not necessarily mean having enough evidence to answer a research question. Learn how to recognize evidentiary gaps, assess whether a design supports the intended conclusion, and determine when a research claim must be narrowed.
Read Guide →Quantitative research is appropriate when answering a question requires numerical measurement, estimation, comparison, or statistical analysis. Learn when it is the strongest methodological fit, what it can establish, and when numerical evidence alone may be insufficient.
Read Guide →Qualitative research is particularly useful when a question concerns experiences, meanings, practices, interactions, or processes that require contextual interpretation. Learn when it is the strongest methodological fit, what different qualitative approaches can establish, and how to assess the adequacy of qualitative evidence.
Read Guide →Using quantitative and qualitative methods together does not automatically improve a study. Learn when mixed methods addresses a genuine evidentiary need, how integration should work, and when one well-designed approach is more defensible.
Read Guide →Quantitative research can investigate why outcomes occur, but statistical relationships alone do not establish causal explanations. Learn which quantitative designs can support explanatory claims, how mechanisms can be investigated, and when the available evidence is insufficient.
Read Guide →Qualitative research can investigate the extent, intensity, and relative prominence of experiences or practices, but it does not automatically support population-level numerical estimates. Learn when qualitative evidence can answer a how much question and when quantitative measurement is necessary.
Read Guide →Access to surveys, interviews, institutional records, and other data can create opportunities for mixed-methods research, but availability alone is not a methodological rationale. Learn how to assess whether existing datasets address a shared research problem, can be integrated meaningfully, and justify the additional analytical complexity.
Read Guide →Reviewers may recommend adding interviews, surveys, or another methodological component to make a study more comprehensive. Learn when such recommendations address genuine evidentiary limitations, when they introduce unnecessary complexity, and how to respond with a defensible methodological rationale.
Read Guide →Adding a second methodological component can expand a study's evidence, but it can also introduce weak measurements, superficial analysis, or unsupported explanations. Learn how to recognize underdeveloped mixed-methods components, assess their consequences, and decide whether strengthening or removing a component would produce a more defensible study.
Read Guide →Combining quantitative and qualitative approaches can strengthen research, but only when integration contributes meaningfully to the intended answer. Learn when one carefully executed method is more defensible than two poorly connected approaches, how to recognize superficial integration, and what to prioritize when selecting a research design.
Read Guide →Researcher competence affects whether a study can be conducted rigorously, but familiarity with a method should not determine the research question. Learn how to balance methodological expertise, training needs, collaboration, and feasibility when choosing between quantitative, qualitative, and mixed-methods approaches.
Read Guide →Sample size affects what a study can establish, but it should not automatically determine whether research is quantitative, qualitative, or mixed methods. Learn how to evaluate sample adequacy according to the intended inference, distinguish statistical power from qualitative information power, and select a defensible design when participant access is limited.
Read Guide →Research timelines affect what can realistically be observed, measured, and analyzed, but the fastest method is not necessarily the most appropriate. Learn how time constraints influence quantitative, qualitative, and mixed-methods designs, when shorter studies can remain rigorous, and when the research question must be revised.
Read Guide →Experimental, quasi-experimental, and observational studies differ mainly in what researchers do with the exposure or intervention and how participants enter comparison conditions. Understanding those differences helps you choose a design that fits both your research question and the strength of inference you hope to make.
Read Guide →Cross-sectional research examines a population or phenomenon within a defined point or period, whereas longitudinal research incorporates observations across time to investigate change, development, or temporal patterns. The better choice depends on what your research question requires you to observe.
Read Guide →Prospective and retrospective research differ in how the study is positioned relative to the data and events being investigated. The distinction affects measurement control, available data, bias, feasibility, and how researchers should describe their design.
Read Guide →Phenomenology, ethnography, grounded theory, and narrative research are not interchangeable labels for interview-based qualitative studies. Each organizes the inquiry around a different purpose, from understanding lived experience to culture, explanatory processes, or stories.
Read Guide →When you collect data affects what relationships, changes, and temporal patterns your study can observe. The number, sequence, and spacing of measurements should follow the process your research question is trying to understand.
Read Guide →Experimental and observational designs can investigate similar research problems, but they differ in how exposures or interventions arise and how causal conclusions are justified. Learn when each approach is appropriate, what randomization contributes, and how to choose a defensible design when experimentation is impractical or unethical.
Read Guide →Prospective and retrospective research differ in how investigators relate data collection to events of interest, but neither approach is automatically stronger. Learn how to choose between following events forward and reconstructing past exposures or outcomes, with attention to measurement quality, bias, feasibility, and causal inference.
Read Guide →Cross-sectional and longitudinal data support different conclusions about populations, relationships, and change. Learn how to select the appropriate data structure, distinguish population trends from individual trajectories, and evaluate the implications of timing, repeated measurement, attrition, and causal inference.
Read Guide →Cross-sectional and longitudinal designs can sometimes investigate the same broad research question, but they may support different conclusions. Learn when their evidence overlaps, why time changes the inference, and how to determine whether the question remains genuinely the same.
Read Guide →Adding research sites can broaden the populations and conditions represented in a study, but it can also introduce differences in participants, implementation, and measurement. Learn when multisite research improves generalizability, how to manage site-level variation, and why more sites do not automatically produce stronger evidence.
Read Guide →Descriptive research does not necessarily require a comparison group. Whether a comparison is useful depends on the research question, the population being described, and the conclusions the study intends to support.
Read Guide →