Chapter 11: Mixed-methods research

Danielle Berkovic

Learning outcomes

Upon completion of this chapter, you should be able to:

  • Understand the definition of mixed-methods research.
  • Identify the three main mixed-methods research designs.
  • Articulate an answerable mixed-methods research question.

What is a mixedmethods study?

The key concept in mixed-methods research is combining qualitative and quantitative research designs and data.

Mixed-methods research requires a purposeful gathering of quantitative and qualitative research methods, including in data collection, data analysis and interpretation of the results. The main word here is ‘mixed’: there must be an intentional combining of both research methods to address the research question.

Planned integration of quantitative and qualitative methods enables researchers to answer research questions that neither quantitative nor qualitative methods could answer on their own. Mixed-methods research draws on the strengths of both quantitative and qualitative research methods, enabling the exploration of diverse perspectives and relationships within the two different types of data.1

How does mixed-methods research fit into a research paradigm?

As described in Chapter 2, a paradigm is a worldview – a framework of beliefs, values and methods.2 There is some debate about whether research paradigms should be bound to a particular methodology. Paradigm purists argue that it is impossible for quantitative and qualitative methods to achieve compatibility, due to the varying types of research questions that the two methods address.3 This perspective suggests that a research project should include only quantitative OR only qualitative methods.

However, researchers using mixed methods argue that it is perfectly logical to use different methods within a single project, blending them as needed to address a particular research question. Many mixed-methods researchers also highlight that paradigms are socially constructed, and that there is no plausible reason these constructs cannot exist within mixed-methods research. As such, mixed-methods researchers encourage other research professionals to consider the evolving relationship between paradigms and methods, in an ever-changing world.4

Chapter 2 describes the four main research paradigms (positivist or scientific, interpretivist or constructivist, radical or critical, and post-structural). Most mixed-methods research reflect post-positivist assumptions, whereby outcomes are perceived to occur based on a combination of factors that interact with each other, rather than assumed to occur in a linear process of cause and effect between exposure and outcome.4 The ‘post’ addition to the positivist paradigm reflects further development from its original concept. Post-positivists maintain the assumption of cause and effect but are willing to identify more complex and non-linear relationships within the data.

The other paradigm (although it is not one of the main four) that primarily exists in the context of mixed-methods research is pragmatism. Pragmatism is oriented towards using multiple research methods but stipulates that the use of these methods should always be guided by existing research problems. Pragmatism values both objective (quantitative) and subjective (qualitative) knowledge to meet research objectives.4 The main reason for adopting a pragmatist position in research is to enable the researcher to collect and analyse their data through a pluralistic lens in order to best answer the research question.

What are the mixed-methods research designs?

There are three mixed-methods research designs: convergent, explanatory and exploratory.

  • A convergent mixed-methods study seeks to combine qualitative and quantitative results with the intention of creating a complete understanding of a particular phenomenon. A convergent mixed-methods study may also validate one set of findings against another, such as comparing participants’ responses on quantitative scales with responses to open-ended qualitative interview questions.
  • An explanatory mixed-methods study seeks to explain quantitative results through qualitative inquiry.
  • An exploratory mixed-methods study seeks to use qualitative results in the development of a quantitative component, which is then tested with study participants.

The terminology used to describe the different mixed-methods designs changes from time to time. When reading an article or textbook written prior to 2021, mixed-methods designs may be referred to as ‘triangulation’, ‘embedded’, ‘explanatory’ or exploratory.5 Table 11.1. presents a comprehensive review of the three mixed-methods designs.

Table 11.1. Summary of the three mixed-methods designs

  Convergent Explanatory Exploratory
Key idea Combine Explain Develop
Seeks to • Combine quantitative and qualitative results with the intention of achieving a complete understanding of the phenomena of interest.

• Validate one set of quantitative or qualitative findings with another set of quantitative or qualitative findings.

• Check whether people provide similar answers on quantitative scales to qualitative open-ended questions.
Explain quantitative results with further qualitative inquiry Utilise qualitative findings in the development of a quantitative research program, which is subsequently tested or implemented.
Data collection Data is collected concurrently; the qualitative and quantitative data collection occur at the same time. Data is collected sequentially: quantitative followed by qualitative. Data is collected sequentially: qualitative followed by quantitative.
Sample considerations Data is being collected simultaneously, and therefore participants are recruited from the same sample.
Unequal sample sizes may mean that there is insufficient statistical power to interpret the quantitative or qualitative results with complete confidence; at the same time, having equal sample sizes is likely to compromise the rigor of the quantitative research.
Participants in the qualitative study are usually sampled from those who have participated in the quantitative component of the mixed-methods study.

The qualitative sample will be smaller than the quantitative sample, which is acceptable.
Participants in the quantitative study should not be recruited from the qualitative phase, in order to avoid confirmatory bias.
Data integration • Look for similarities and differences in the quantitative and qualitative research individually.

• Consider how the individual results confirm or diverge from each other.

• Discuss these similarities and differences to complete your understanding of the phenomena of interest.
• Identify the quantitative results that need to be further integrated.

• Purposefully explore these results, using qualitative methods.

• Discuss how the qualitative results explain your quantitative findings.
• Use your qualitative results to identify and plan a follow-up quantitative study; e.g. trial a patient-reported outcome measure.

• Pilot and test the quantitative component with a new sample of participants.

• Build on the qualitative findings.
Suggestions for displaying results* A table with side-by-side columns highlighting similarities and differences between the quantitative and qualitative studies. A table with side-by-side columns, with one column displaying a summary of the quantitative results, and the second column displaying qualitative results. Use arrows to connect the development of the quantitative study with the qualitative results.
Advantages Intuitive and timely because participants are recruited from the same sample.

Facilitates team research, with quantitative and qualitative skills required for the research as a whole.

Gives a ‘voice’ to those who have participated in the quantitative component of the research.
May appeal to quantitative researchers because results that are familiar can be followed up through qualitative research.

A good opportunity to explore emergent findings in greater detail.
Useful when further quantitative investigation is warranted but it is not yet clear what form that should take.

Able to produce a new instrument, measure, variable or intervention, based on the qualitative phase.
Disadvantages The different sample size requirements can be challenging to navigate.

Merging numerical data with words can be challenging.

Expertise is required in explaining the similarities and differences between the datasets.
It can be time-consuming to conduct two phases of research.

The qualitative study cannot be planned in advance and so it requires innovation and flexibility.
It can be time-consuming to conduct two phases of research, especially when a new round of participants needs to be recruited.

The quantitative study cannot be planned before the qualitative analysis has taken place, so it requires the ability to be innovative and flexible.

Requiring two different samples means that each step of the study has its own limitations.

*This can also be created using appropriate imagery.

For example, in Patient-centred innovation for multimorbidity care: a mixed-methods, randomised trial and qualitative study of the patients’ experience,6 both a randomised trial (quantitative) and interviews (qualitative) were conducted to address two research aims: (1) to assess the effectiveness of the intervention in relation to relevant patient-reported outcomes, and (2) to understand what worked and did not work about the intervention for patients. A one-hour case conference intervention was developed for the randomised trial, involving a nurse exploring what was important to patients. A planned and coordinated case conference followed with the patients’ healthcare professionals (for example, psychiatrist, social worker and dietitian) based on this feedback. The nurse, the patient and all relevant health professionals then met for over an hour to focus on the patient’s goals and to co-create a care plan. Outcomes assessed included self-efficacy in managing chronic disease, health status, quality of life, psychological distress and health behaviour.

For the qualitative component of this project, semi-structured interviews were conducted, with purposively selected patients (e.g. by age, sex and type of patient) as the qualitative component of the research in the trial intervention arm. The researchers analysed the data using thematic analysis.

From a quantitative research perspective, the intervention provided no statistically significant improvement. However, five themes were identified from the interviews: (1) patients valued the team developed as part of the intervention, (2) patients felt more supported, (3) receiving a follow-up plan was helpful, (4) being offered a change in the treatment plan was refreshing, and (5) patients perceived positive outcomes from the intervention.

Without the qualitative evaluation of this intervention, the trial would have been considered unsuccessful. Yet, by seeking participant feedback, it became evident that the trial did in fact improve patients’ healthcare-seeking experiences and perceptions, in terms of multimorbidity, in ways not captured through quantitative measures. The researchers now know what works and what does not work about the intervention and can use this data to tailor future trials or implementation.

Table 11.2. provides three more examples of mixed-methods studies across the health and social care sector.

Table 11.2. Examples of mixed-methods research

Title The social cure of social prescribing: a mixed-methods study on the benefits of social connectedness on quality and effectiveness of care provision7 A mixed methods case study exploring the impact of membership of a multi-activity, multicentre community group on social wellbeing of older adults8 Using an exploratory sequential mixed method design to adapt an Illness Perception Questionnaire for African Americans with diabetes: the mixed data integration process9
First author and year Kellezi, 2019 Lindsay-Smith, 2018 Shiyanbola, 2021
CC Licence CC BY NC 4.0 CC BY 4.0 CC BY 4.0
Mixed-methods study type Convergent Explanatory Exploratory
Aim • Qualitative methods: To gain a deeper insight into perceptions or understandings of the social factors influencing health and presentation to primary care

• Quantitative methods: To evaluate the overall efficacy of the created pathway to healthcare usage
• Quantitative methods: To examine whether loneliness and social support of new members of Life Activities Clubs changes in the year after joining

• Qualitative methods: To conduct an in-depth exploration of how social wellbeing changes in new and longer-term members of Life Activities Clubs
• Qualitative methods: To address the sociocultural contexts and assess the perceptions of type 2 diabetes African Americans.

• Quantitative methods: To culturally adapt the Illness Perception Questionnaire-Revised (IPQ-R) for African Americans with type 2 diabetes.
Why a mixed-methods study was conducted Ageing populations and increasing demand for health services are two major challenges facing the National Health Service in the United Kingdom, exacerbated by increasing prevalence of loneliness. This study investigated the degree to which healthcare professionals and patients recognised their experiences with social (dis)connection and was able to measure the impact of group membership on experiences of loneliness. Social wellbeing factors such as loneliness and social support have a major impact on the health of older adults and can contribute to physical and mental wellbeing. This study combined a survey assessing loneliness, social support and focus group data to further explore the positive and negative impacts of joining community groups in older age. Mixed-method approaches offer opportunities to study contextual factors such as culture, perceptions and beliefs qualitatively, and to develop quantitative measures. Although this has been done previously to develop and adapt questionnaires, the methods used have not been thoroughly described. This study adapted the IPQ-R to address sociocultural contexts of African Americans with type 2 diabetes, and to evaluate the congruence between qualitative and quantitative data in the mixed-methods approach.
Study setting/country • Semi-structured interviews (n=35)

• 18-month pathway implementation and survey measurements of belonging, loneliness and health service use

• Quantitative survey collected at 3 time points across a 12-month period, investigating the effects of joining a community group on social wellbeing of older adults (n=28

• Focus group (n=11)
• Qualitative focus groups conducted with 40 participants exploring beliefs about type 2 diabetes.

• Quantitative survey of African Americans with type 2 diabetes

• Survey items written and adapted based on focus group findings.
Analysis • Realistic thematic analysis

• Statistics: ANOVA, Bonferroni-corrected t-tests
• Linear mixed models

• Thematic analysis
• Deductive content analysis

• Descriptive statistics, item mean scores, and item-total correlations.
Key themes • Qualitative results: (1) GP perspective – social factors and the need for a holistic service; (2) patients’ perspective – relationship with healthcare workers and building social connections

• Quantitative results: Psychosocial factors are important for predicting reductions in primary care usage (p=0.022).
• Quantitative results: There was a significant reduction in loneliness (p=0.023) and a trend toward an increase in social support (p=0.056) in the first year after joining a community group

• Qualitative results: Group membership provided important opportunities for developing new and diverse social connections through shared interest and experience, which was key to feeling supported.
• Qualitative results: timeline perception of diabetes not going away and diabetes goes away if you lose weight, consequences of diabetes, personal control domain, the importance of medications, and understanding diabetes by family members.

• The matching of qualitative themes to survey domains included the timeline, consequences, personal control, treatment control, illness coherence, and emotional representations.


The three types of mixed-methods research can be conducted across health and social care disciplines, with a multidisciplinary team. Each type of mixed-methods study has its own strengths and limitations, but all integrate quantitative and qualitative research methods to develop a thorough picture of the phenomena under investigation.


  1. Shorten A, Smith J. Mixed methods research: expanding the evidence base. Evid Based Nurs. 2017;20(3):74-75. doi:10.1136/eb-2017-102699
  2. Donmoyer R. Paradigm. In: Given LM, ed. The SAGE Encyclopedia of Qualitative Research Methods. SAGE; 2008:591-595. doi:10.4135/9781412963909
  3. Liu Y. Paradigmatic compatibility matters: a critical review of qualitative-quantitative debate in mixed methods research. SAGE Open. 2022;12(1). doi:10.1177/21582440221079922
  4. Dawadi S, Shrestha S, Giri RA. Mixed-methods research: a discussion on its types, challenges, and criticisms. Journal of Practical Studies in Education. 2021;2(2):25-36. doi:10.46809/jpse.v2i2.20
  5. Creswell JW, Plano Clark VL. Designing and Conducting Mixed Methods Research. SAGE; 2007.
  6. Stewart M, Fortin M, Belle Brown J, et al. Patient-centred innovation for multimorbidity care: a mixed-methods, randomised trial and qualitative study of the patients’ experience. Br J Gen Pract. 2021;71(705):e320-e330. doi: 10.3399/bjgp21X714293
  7. Kellezi B, Wakefield JRH, Stevenson C, et al. The social cure of prescribing: a mixed-methods study on the benefits of social connectedness on quality and effectiveness of care provision. BMJ Open. 2019;9(11):e033137. doi: 10.1136/bmjopen-2019-033137
  8. Lindsay-Smith G, O’Sullivan G, Eime R, Harvey J, van Ufellen JGZ. A mixed-methods case study exploring the impact of membership of a multi-activity, multicentre community group on social wellbeing of older adults. BMC Geriatrics. 2018;18:226. doi: 10.1186/s12877-018-0913-1
  9. Shiyanbola OO, Rao D, Bolt D, Brown C, Zhang M, Ward E. Using an exploratory sequential mixed methods design to adapt an Illness Perception Questionnaire for African Americans with diabetes: the mixed data integration process. Health Psychol Behav Med. 2021;9(1):796-817. doi: 10.1080/21642850.2021.1976650