Sensitivity Analysis-Based Purposive Sampling
Also known as: purposive sampling with sensitivity checks, robust purposive sampling, sensitivity-tested purposive selection
Sensitivity analysis-based purposive sampling extends conventional purposive sampling by systematically testing whether key findings or case-selection decisions change when the inclusion criteria, selection logic, or boundary conditions are altered. It applies the logic of sensitivity analysis — standard in quantitative research and systematic reviews — to qualitative case selection, giving researchers explicit evidence of how robust their purposive choices are to plausible alternative selection rules.
Read the full method
Sign in with a free account to read this section.
Method map
The neighbourhood of related methods — select a node to explore.
When to use it
Use sensitivity analysis-based purposive sampling when the purposive selection criterion is contested, ambiguous, or operationally uncertain — for example, when defining 'high-performing', 'vulnerable', or 'experienced' depends on thresholds that could reasonably vary. It is especially valuable in policy-relevant or applied research where stakeholders may question why particular cases were chosen, and in mixed-methods studies where the qualitative component must be demonstrably aligned with the quantitative component. Do NOT use this approach as a substitute for transparent initial criterion definition — if the primary criterion is vague from the outset, sensitivity analysis cannot rescue the design. Also avoid it when sample size is so small (fewer than five cases) that alternative selection rules produce entirely different non-overlapping samples, making comparison meaningless.
Strengths & limitations
- Strengthens methodological transparency by making the selection logic auditable and variation in findings explicitly reported.
- Reduces the risk that conclusions rest on an arbitrary or contestable operationalization of the selection criterion.
- Bridges qualitative and quantitative methodological cultures by importing robustness-checking norms into purposive sampling.
- Provides a structured response to peer reviewer or committee challenges about why specific cases were chosen.
- Improves credibility of findings in policy and applied research contexts where sampling decisions are scrutinized.
- Requires additional time and effort to construct, analyze, and compare multiple alternative samples or selection scenarios.
- Does not eliminate subjectivity in purposive sampling — it redistributes it to the choice of which alternative criteria to test.
- With very small samples typical in qualitative work, alternative criteria may produce entirely disjoint case sets, limiting meaningful comparison.
- The additional complexity may obscure rather than clarify the research narrative if not reported concisely.
Frequently asked
How is this different from regular purposive sampling?
Regular purposive sampling selects cases according to one defined criterion and stops there. Sensitivity analysis-based purposive sampling additionally tests whether findings or selected cases would differ if the criterion were operationalized differently. The baseline selection process is identical; what changes is the explicit robustness-checking step that follows.
How many alternative criteria should I test?
Two to four alternatives is generally sufficient. The goal is to cover the range of plausible, defensible operationalizations a knowledgeable colleague might propose — not to exhaust every possible variant. Diminishing returns set in quickly, and testing too many alternatives can obscure rather than clarify the findings.
Does this approach require collecting data from all alternative samples?
Not necessarily. If the dataset already exists (e.g., a case archive or document corpus), you can apply alternative selection rules to the existing data. If data must be collected from participants, the practicality of collecting full datasets for each alternative is usually low; in that case, sensitivity analysis is applied to the selection logic and preliminary thematic findings rather than full separate datasets.
Is this method suitable for grounded theory or phenomenology?
It fits less naturally with grounded theory, where theoretical sampling is emergent and driven by developing theory rather than pre-specified criteria. For phenomenology, where the criterion is typically direct lived experience of the phenomenon, there may be fewer plausible alternatives to test. Sensitivity analysis-based purposive sampling is most valuable when the selection criterion is a constructed category with real definitional ambiguity.
Where should I report the sensitivity analysis results?
In the methods section, after describing the primary sample and selection criterion, add a subsection documenting the alternative criteria tested and whether the resulting case sets or preliminary findings differed meaningfully. If findings were stable, a brief statement suffices; if sensitive, discuss how the final selection was determined and why.
Sources
- Patton, M. Q. (2015). Qualitative Research and Evaluation Methods (4th ed.). Sage Publications. ISBN: 978-1412972123
- Teddlie, C., & Yu, F. (2007). Mixed methods sampling: A typology with examples. Journal of Mixed Methods Research, 1(1), 77–100. DOI: 10.1177/2345678906292430 ↗
How to cite this page
ScholarGate. (2026, June 3). Sensitivity Analysis-Based Purposive Sampling. ScholarGate. https://scholargate.app/en/survey-methodology/sensitivity-analysis-based-purposive-sampling
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Deviant Case SamplingSurvey Methodology↔ compare
- Maximum Variation SamplingSurvey Methodology↔ compare
- Purposive samplingSurvey Methodology↔ compare
- Snowball SamplingSurvey Methodology↔ compare
- Typical Case SamplingSurvey Methodology↔ compare