Designing a Study You Can Defend
Documents and existing texts can provide the principal evidence for a research study without requiring interviews, surveys, or observations. Learn when documentary data are sufficient, how to evaluate their origins and limitations, and how to distinguish documents as primary evidence from documents used merely as background literature.
Read Guide →
Designing a Study You Can Defend
Research documents extend beyond printed reports and official policies. Emails, digital records, websites, meeting minutes, photographs, and other recorded materials may qualify depending on the research question. Learn how to define a document, distinguish documentary evidence from other data, and establish defensible boundaries for a research corpus.
Read Guide →
Designing a Study You Can Defend
A document corpus is more than a collection of available files. Learn how to establish its boundaries, define eligible documents, identify sources, manage versions and duplicates, document retrieval decisions, and determine whether the resulting corpus can support your research questions.
Read Guide →
Designing a Study You Can Defend
Should researchers analyze every available document or select a sample? Learn how corpus size, research objectives, analytical depth, representativeness, and resource constraints affect the decision, and how to justify either approach without confusing complete analysis with complete coverage of the documentary population.
Read Guide →
Designing a Study You Can Defend
Public social media posts can provide documentary evidence about communication, institutional representations, and online discourse. However, public accessibility does not automatically establish unrestricted research use. Learn how to evaluate social media content as documentary data, establish a defensible corpus, address consent and privacy, and interpret findings without confusing platform activity with wider public opinion.
Read Guide →
Designing a Study You Can Defend
Quantitative content analysis measures defined features of communication, while qualitative content analysis examines meaning, context, and patterns of interpretation. Mixed-methods content analysis integrates numerical and qualitative evidence for a common research purpose. Learn how to choose the appropriate approach, develop coding procedures, and avoid confusing numerical counts with meaningful interpretation.
Read Guide →
Designing a Study You Can Defend
Document analysis does not automatically require interviews, surveys, or observations. Additional data sources become important when documents cannot adequately establish the behaviors, experiences, implementation processes, or outcomes central to the research question. Learn when triangulation is justified, how to integrate evidence, and why agreement across sources is not always necessary or sufficient for credible findings.
Read Guide →
Designing a Study You Can Defend
Secondary data analysis may be preferable when existing datasets provide suitable measurements, adequate population coverage, and stronger evidence than a feasible new study could collect. Learn how to evaluate data quality, costs, accessibility, analytical limitations, and research objectives before deciding whether to reuse existing information or collect new data.
Read Guide →
Designing a Study You Can Defend
A dataset may contain relevant variables yet remain poorly suited to a new research question because it was originally created for another purpose. Learn how to evaluate conceptual alignment, measurement, population coverage, timing, and data-generation procedures, and how to decide whether the question should be retained, refined, or abandoned.
Read Guide →
Designing a Study You Can Defend
Secondary datasets can support research questions their original investigators never anticipated. However, new analytical possibilities do not automatically establish valid new interpretations. Learn how to assess construct alignment, temporal structure, confounding, sampling, and the distinction between exploratory discovery and confirmatory analysis.
Read Guide →
Designing a Study You Can Defend
Secondary datasets often contain indirect indicators rather than direct measures of the constructs researchers want to investigate. Learn when proxy variables are appropriate, how to justify their relationship to the intended construct, assess measurement limitations, and prevent misleading interpretations.
Read Guide →
Designing a Study You Can Defend
Missing variables can undermine causal inference even when a secondary dataset contains thousands of observations. Learn how to identify essential confounders, distinguish unmeasured variables from missing values, evaluate adjustment strategies, and determine when residual confounding makes a proposed analysis unsuitable.
Read Guide →
Designing a Study You Can Defend
Existing datasets rarely contain every variable a researcher would ideally collect. Learn when refining a research question is methodologically defensible, how to distinguish conceptual improvement from result-driven changes, and when the available data are too limited to justify adaptation.
Read Guide →
Designing a Study You Can Defend
Not every existing dataset can support a defensible secondary analysis. Learn how to distinguish manageable limitations from fundamental design problems, evaluate whether the intended research question remains answerable, and decide when to revise or abandon a proposed study.
Read Guide →
Designing a Study You Can Defend
Medical records, administrative databases, and other routinely collected data can provide valuable research evidence, but their original purpose may differ from the needs of a scientific investigation. Learn how to evaluate their suitability, measurement quality, completeness, population coverage, and ethical use.
Read Guide →
Designing a Study You Can Defend
Incomplete routine records can distort research findings even when datasets contain thousands of observations. Learn how to distinguish missing information from unrecorded events, investigate documentation patterns, and select defensible analytical responses.
Read Guide →
Designing a Study You Can Defend
Record linkage can connect information about the same individuals, events, or organizations across datasets. Learn when linkage is methodologically necessary, how to assess whether it is feasible, and when its risks may outweigh its benefits.
Read Guide →
Designing a Study You Can Defend
Existing registries and cohorts can provide valuable research data without requiring investigators to recruit an entirely new sample. Their suitability depends on whether the population, measurements, follow-up, and data quality can support the intended research question.
Read Guide →
Designing a Study You Can Defend
A registry may contain extensive records without adequately representing the population you want to study. Learn how to evaluate population alignment, identify meaningful coverage differences, and determine how broadly your findings can reasonably apply.
Read Guide →
Designing a Study You Can Defend
A registry can support a nested case-control study when it defines a suitable source cohort and provides reliable event timing and exposure information. Learn how to construct risk sets, select controls, and analyze the resulting data without losing the logic of the underlying cohort.
Read Guide →
Designing a Study You Can Defend
Registry variables may be introduced, discontinued, or collected only during certain periods. Learn how to distinguish structural missingness from ordinary missing data, establish valid analysis periods, and avoid misleading comparisons.
Read Guide →
Designing a Study You Can Defend
The unit of analysis determines what your study is actually analyzing and what your conclusions concern. Learn how to identify the appropriate unit, distinguish it from the unit of observation, and avoid errors involving clustered or repeated data.
Read Guide →
Designing a Study You Can Defend
Different research questions require different analytical units, even when they use similar data. Compare individual, household, classroom, institutional, community, and country-level analysis to determine which level supports your intended conclusions.
Read Guide →
Designing a Study You Can Defend
The entities from which researchers collect observations are not always the entities they analyze. Learn how to distinguish units of observation from units of analysis, recognize legitimate mismatches, and choose methods that support the intended conclusions.
Read Guide →
Designing a Study You Can Defend
Misidentifying the unit of analysis can produce misleading sample sizes, inappropriate statistical tests, and conclusions at the wrong level. Learn how to recognize these errors, assess their consequences, and determine whether an existing analysis can be corrected.
Read Guide →
