Concurrent Embedded Mixed Methods Design
Also known as: embedded mixed methods, nested mixed methods design, concurrent nested design, CEMM
The concurrent embedded mixed methods design collects quantitative and qualitative data at the same time, but assigns unequal priority to the two strands: one (usually quantitative) serves as the primary study, while the other (usually qualitative) is nested inside it to answer a supplementary question. The embedded strand does not stand alone; it provides a different perspective on the same phenomenon within a single unified study.
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.
+30 more
When to use it
Use the concurrent embedded design when a primary study (often a quantitative experiment or survey) is already planned or underway and a secondary qualitative (or quantitative) question cannot wait for a follow-up study. It is well-suited for adding participant-experience data to a clinical trial, an evaluation, or a large survey, or for embedding a quantitative measure within a primarily qualitative study to increase precision on one dimension. Do NOT use it when the secondary strand deserves equal status — use concurrent triangulation instead. Avoid it when full integration is needed throughout analysis, not just at interpretation; or when the secondary strand's sample is too small to draw any meaningful conclusions about the sub-question.
Strengths & limitations
- Allows a secondary question to be answered within a single study, saving time and resources compared to sequential or separate designs.
- Keeps data collection concurrent, so both strands reflect the same moment in time and the same study context.
- Flexibility: either strand — quantitative or qualitative — can serve as the primary, depending on the research question.
- Particularly efficient for adding process or experience data to experimental or intervention studies without redesigning the main study.
- Produces findings with both statistical breadth (primary strand) and interpretive depth (embedded strand).
- Unequal weighting means the embedded strand's findings are by design subordinate; they cannot overturn or fully challenge the primary strand's conclusions.
- The embedded sample is usually a sub-sample, so transferability of the secondary findings may be limited.
- Integrating two methodologically different strands at the interpretation stage requires substantial researcher skill and explicit design decisions made before collection begins.
- If the embedded strand grows in scope during the study, resource and timeline conflicts with the primary strand can arise.
Frequently asked
How is the concurrent embedded design different from concurrent triangulation?
In concurrent triangulation both strands have equal priority and the goal is to cross-validate findings. In the embedded design one strand is explicitly primary and the other is nested inside it to answer a supplementary question. If you want to compare and validate, use triangulation. If one strand serves the other, use the embedded design.
Which strand should be primary — quantitative or qualitative?
The primary strand should reflect the main research question. If the study's central aim is to test a hypothesis or measure outcomes, quantitative is primary. If the central aim is to interpret a process or construct meaning, qualitative is primary. Either combination is methodologically legitimate.
When does integration happen in this design?
Integration occurs at the interpretation stage — after each strand has been analysed separately and independently. The researcher then connects the two sets of findings in a combined discussion, using the embedded strand to explain, extend, or contextualise the primary strand's results.
Can the embedded strand use a different sample from the primary strand?
Yes. The embedded strand can draw on a purposive sub-sample of primary study participants, or in some designs it can involve a different but related group. What matters is that the connection between the two samples is theoretically justified and reported transparently.
Is the concurrent embedded design suitable for a dissertation?
It can be, but only if the researcher has the skills and resources to manage two simultaneous data collection streams and to carry out the integration analytically. Many dissertation projects underestimate the coordination burden. Consider whether a sequential design would be more manageable while still addressing the research questions.
Sources
- Creswell, J. W., & Plano Clark, V. L. (2011). Designing and Conducting Mixed Methods Research (2nd ed.). Sage. ISBN: 978-1412975179
- Creswell, J. W., Plano Clark, V. L., Gutmann, M. L., & Hanson, W. E. (2003). Advanced mixed methods research designs. In A. Tashakkori & C. Teddlie (Eds.), Handbook of Mixed Methods in Social and Behavioral Research (pp. 209–240). Sage. link ↗
How to cite this page
ScholarGate. (2026, June 3). Concurrent Embedded Mixed Methods Design. ScholarGate. https://scholargate.app/en/research-design/concurrent-embedded-mixed-methods-design
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.
- Concurrent Triangulation Mixed Methods DesignResearch Design↔ compare
- Explanatory Sequential Mixed Methods DesignResearch Design↔ compare
- Exploratory Sequential Mixed Methods DesignResearch Design↔ compare
- Multilevel Mixed Methods DesignResearch Design↔ compare
- Multiphase Mixed Methods DesignResearch Design↔ compare
- Transformative Mixed Methods DesignResearch Design↔ compare