Ask Mallard
Study design

Convergent mixed-methods study

4 min read

A convergent mixed-methods study collects qualitative and quantitative evidence in the same phase, then brings their findings together.

NHMRC EVIDENCE LEVEL · 2009Outside the NHMRC hierarchy
Why this level?not one of the five research areas this hierarchy covers. NHMRC 2009 source

The study integrates qualitative accounts and quantitative findings. Judge each strand by its own design and the combined inference by how the strands are connected; mixing methods does not raise causal certainty.

Fit

When to use it, and when not to

Use it when

  • You need numbers and contextual accounts about the same issue during one study phase.
  • Neither strand needs the other results before data collection begins.

Not when

Before you start

What you need

Decide these first
  1. A design for each strandDefine the quantitative target and qualitative question.
  2. A link between samples and constructsState whether the same people participate and which findings can be compared.
  3. An integration planPlan a joint display or another explicit way to compare findings.
  4. A quantitative missing-data planName the assumption and how departures will be assessed.
It rests on these
  1. Each strand meets its own quality standards.How to check: Check the quantitative design and qualitative sampling and analysis separately.
  2. The strands address a shared question.How to check: Trace how their combination changes the interpretation, including disagreement.
  3. Missing quantitative data follow the stated assumption.How to check: Missing completely at random is unlikely when service disruption creates gaps. Missing at random is plausible if recorded factors explain gaps. Multiple imputation under MAR may help, but it is not automatically better than complete records. If missing not at random is plausible, use a delta or tipping-point sensitivity analysis.

Plain language

How it works

Collect both strands in the same broad phase. Analyze each using its own methods, then merge the findings around shared constructs. A joint display can place estimates beside contextual accounts and record where they disagree.

The study structure
Collect both strands in one phase; then Analyze each strand on its own terms; then Merge findings around shared constructs; then Explain agreement and disagreement.Convergent mixed-methods studyCollect both strands in one phaseAnalyze each strand on its own termsMerge findings around shared constructsExplain agreement and disagreement
Conceptual diagram. It shows the structure of the idea, not data from any study.
What the answer means

Fetters and colleagues describe convergent integration. Guetterman and colleagues show how joint displays support combined inferences. Findings may conflict because of sampling, measurement or a real difference in perspective; explain the conflict rather than forcing agreement.

Worked example

A worked example

Invented for illustration
Setting
A service measures appointment access and interviews patients during the same phase.
Question
How do measured access and patient accounts fit together?
Approach
Analyze both strands, then place access results beside accounts of transport and scheduling.
Result
80 of 100 sampled patients return the survey, 80 in 100. Interviews describe barriers that the average access measure misses.
What it means
The response share describes survey participation. A joint display explores agreement and disagreement without treating interview themes as population rates.

In practice

Recent studies PubMed search · not vetted

Searching PubMed…

Watch out

Common mistakes

The one to remember

Parallel data collection is not integration; agreement and disagreement must be examined, and each strand needs a defensible design.

  • Reporting two strands without bringing them together.Instead: Show the integration step and what new inference it supports.
  • Treating purposive interviewees as a representative sample.Instead: Describe their selection and distinguish their accounts from population estimates.

Inside Mallard

How Mallard uses this

Plans do not link to this design yet. Learn search and the Atlas offer it as a reference.

No Mallard code example points to this page.
Atlas node design.mixed_convergent, the id a plan cue records.

How to report it

No reporting guideline dedicated to convergent mixed-methods study was found in a PubMed search on 2026-11-07. GRAMMS covers mixed-methods reporting; SRQR covers the qualitative strand. Report the shared question, timing, samples, strand methods, integration display and inferences, including disagreement. A reporting guideline is not a design manual: use it to make the study transparent, not as a substitute for careful design. Check the target journal's own requirements as well, which this page cannot know.

Related Learn pages

Related designs and methods

Evidence

Sources & further reading

  1. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls (opens in a new tab) · BMJ · doi 10.1136/bmj.b2393
  2. Achieving integration in mixed methods designs-principles and practices (opens in a new tab) · Health Serv Res · doi 10.1111/1475-6773.12117
  3. Integrating Quantitative and Qualitative Results in Health Science Mixed Methods Research Through Joint Displays (opens in a new tab) · Ann Fam Med · doi 10.1370/afm.1865
  4. The quality of mixed methods studies in health services research (opens in a new tab) · J Health Serv Res Policy · doi 10.1258/jhsrp.2007.007074
  5. Standards for reporting qualitative research: a synthesis of recommendations (opens in a new tab) · Acad Med · doi 10.1097/ACM.0000000000000388
Prepared with AI assistance. PubMed titles, authors, years and DOIs checked on 2026-11-07. Record verified, confirm it supports this use. No independent professional approval is claimed.
Last source review: 2026-11-07
AI-generated educational content
Mallard uses reputable methodological and reporting sources, but this material may contain errors or omit important context. Verify important methodological decisions with the cited sources and, when appropriate, a qualified research methodologist or statistician.