Why do mixed methods research

Metrics details. Recently, there has been a surge of international interest in combining qualitative and quantitative methods in a single study — often called mixed methods research. It is timely to consider why and how mixed methods research is used in health services research HSR.

Documentary analysis of proposals and reports of 75 mixed methods studies funded by a research commissioner of HSR in England between and Face-to-face semi-structured interviews with 20 researchers sampled from these studies. In the documentation, comprehensiveness was the main driver for using mixed methods research, with researchers wanting to address a wider range of questions than quantitative methods alone would allow.

Interviewees elaborated on this, identifying the need for qualitative research to engage with the complexity of health, health care interventions, and the environment in which studies took place. Motivations for adopting a mixed methods approach were not always based on the intrinsic value of mixed methods research for addressing the research question; they could be strategic, for example, to obtain funding. Mixed methods research was used in the context of evaluation, including randomised and non-randomised designs; survey and fieldwork exploratory studies; and instrument development.

Studies drew on a limited number of methods — particularly surveys and individual interviews — but used methods in a wide range of roles. Its use is driven by pragmatism rather than principle, motivated by the perceived deficit of quantitative methods alone to address the complexity of research in health care, as well as other more strategic gains.

Methods are combined in a range of contexts, yet the emerging methodological contributions from HSR to the field of mixed methods research are currently limited to the single context of combining qualitative methods and randomised controlled trials. Health services researchers could further contribute to the development of mixed methods research in the contexts of instrument development, survey and fieldwork, and non-randomised evaluations.

Both qualitative and quantitative methods can be used in the same study. This is variously called 'multi-method', 'mixed methods' or 'multiple methods' research [ 1 ], although there is a move to standardise terminology and use the label 'mixed methods research' for studies combining qualitative and quantitative methods [ 2 ].

There is an established body of knowledge about mixed methods research, discussing why this approach is used, how it can be used, and highlighting the challenges of using it in theory and in practice [ 3 , 4 ].

Recently, there has been an increased interest in mixed methods research in the fields of social and educational research both in the United Kingdom UK [ 5 — 9 ] and North America [ 10 , 11 ]. Over the last two years, journals devoted solely to mixed methods research have been launched — the Journal of Mixed Methods Research, and the International Journal of Multiple Research Approaches. Over the next two years at least half a dozen books on mixed methods research will be published by researchers in the UK, Europe and North America.

Thus it is timely to consider why and how health services researchers use mixed methods research. This will help researchers to understand the relevance of the established and emerging body of knowledge on mixed methods research to their work. The aims of this paper are to describe why and how researchers undertake mixed methods studies in HSR and to consider whether researchers are exploiting the full range of justifications and types of approaches available to them.

Historically, health services researchers in the UK have used quantitative methodology. In the past decade or so they have welcomed qualitative methodology, detailing the contribution it can make to research in health care [ 12 ]. Health services researchers have also combined qualitative and quantitative research in a single study and contributed to a renewed interest in mixed methods research, by making the case for mixed methods research in HSR [ 13 ] and giving overviews of the key issues in mixed methods research in HSR [ 14 — 16 ].

The main contribution of the HSR community in the UK to the body of knowledge about mixed methods research has been in the use of qualitative research alongside randomised controlled trials RCTs. Health services researchers have detailed the contribution of qualitative methods within a pilot RCT [ 18 ]; encouraged the use of mixed methods within an iterative phased approach to trials [ 19 ] and within contextual evaluations undertaken alongside trials [ 20 ]; used qualitative research to improve the design and conduct of a trial [ 21 ]; described the challenges of undertaking a process evaluation [ 22 ]; detailed the process of exploring apparent discrepancies between findings from the qualitative and quantitative components of a pilot trial [ 23 ]; and described how to integrate largely qualitative process evaluations with trial data and findings [ 24 ].

Mixed methods research has been discussed in the HSR literature, but there is little information about how commonly it is used, and why and how it is used in practice. When researchers in HSR have offered justifications for using a mixed methods approach, these have usually been related to the need for comprehensiveness. Researchers have pointed to the complexity of health care and the need for a range of methodologies to understand and evaluate these complexities [ 12 , 16 , 18 , 19 , 25 ].

There has also been a growing recognition of the importance of understanding the impact of the delivery and organisation of health services, with a focus on processes as well as outcomes, and the range of methodological approaches required to do this [ 26 ].

However, there are many justifications for using mixed methods research, apart from comprehensiveness, including increased confidence in findings, ensuring that disempowered groups in society are heard, and developing or facilitating one method by guiding the sampling, data collection or analysis of the other [ 14 , 27 ]. There are also many different ways of designing mixed methods studies.

Many researchers have described the range of potential roles of qualitative and quantitative methods within a mixed methods study. We have displayed these in a pragmatic way, following the stages of research from development to dissemination [ 28 ] see Table 1. The characteristics of mixed methods studies have been described in terms of the purpose of combining methods, the priority of methods within a study, and the sequence in which methods are used [ 29 ], with purposes including complementarity, confirmation, development [ 30 ].

In this paper we describe why and how researchers undertake mixed methods studies in HSR in the context of this body of literature. A mixed methods design was used to explore the use of mixed methods research in HSR.

A documentary analysis of the proposals, reports and publications from mixed methods studies in HSR was undertaken to explore how mixed methods studies were undertaken. Interviews were undertaken with researchers from these studies to explore why researchers undertook mixed methods studies in the way they did.

The two methods were used sequentially, with the documentary analysis undertaken before the interviews. The two methods were given equal priority. In terms of the purposes of combining methods, methods were combined both for complementarity, where each method addressed a different aspect of the research question, and for development where the quantitative component facilitated sampling for the qualitative component [ 30 ].

The Department of Health is a key commissioner of HSR in England and summaries of funded studies are listed on their website [ 31 ]. This website was used as the source of HSR studies for this research. All summaries of research studies listed under ten programmes of research on the Department of Health website were read by one of the authors AOC. Studies using primary health research were included.

Studies undertaken as single studies rather than as part of a programme, initiative or fellowship were included because detailed summaries were available for the former whereas summaries were not available or had no methodological detail for latter types of studies.

Projects with a quantitative and a qualitative component were classified as mixed methods studies. Details of this are described elsewhere [ 27 ]. When a mixed methods study was identified, the lead researcher of each study was written to with a request for the research proposal, the final report for completed studies, and any emerging publications.

Documentation was read by one researcher AOC and a number of issues around how the study had been undertaken were coded on a data extraction form. Issues included the methods used, roles of methods, priority and purpose of methods, approach taken to integration, quality of components, and types of publications emerging.

The issues of relevance to this paper were whether a justification was given for using mixed methods and the roles of each method within a study. The data extraction form was structured, based on roles discussed in the literature. There was space for free-text comments for each structured item.

For example, if a justification was given for using mixed methods research then this was written on the data extraction form.

The aim of the qualitative component of the study was to explore why researchers in HSR undertook studies in the way they did, and explore facilitators and barriers to this approach.

Therefore it was relevant to interview researchers who had undertaken mixed methods studies in HSR. Researchers working on the studies included in the documentary analysis were sampled. Researchers' names were available from lists of applicants on proposals, lists of authors on reports, and lists of authors on articles. Purposive sampling was undertaken [ 32 ] to include a range of types of researchers — qualitative and quantitative researchers — and a range of types of mixed methods studies.

An attempt was made to maximise variation within the sample by including research situated in different types of departments such as nursing, research units, primary care, and psychiatry; and research funded from different Department of Health programmes.

Face-to-face semi-structured interviews were undertaken with researchers, focusing on their views of mixed methods studies generally and on the study included in the documentary analysis. Interviews lasted approximately one hour, were recorded, and transcribed verbatim. For the documentary analysis, codes from the data extraction form were entered into SPSS.

Percentages of studies in each category were calculated. Free-text comments were transcribed from the data extraction form into Word. Comments were read, themes were identified, and the frequency of each theme across the studies was counted. The interviews were analysed using the first stages of Framework [ 33 ]. Framework was chosen as a suitable approach because it allows the researcher to explore their agenda explicitly while also allowing other themes to emerge from the analysis.

A thematic framework was developed based on the research question and familiarisation with the first few transcripts, and then applied to each transcript using the computerised qualitative software package WinMAX [ 34 ]. The data extracts for each theme or sub-theme were read and further coding was undertaken within them to organise and understand the data. Themes included paradigms, team working, quality of studies, justifications for using mixed methods and publishing studies.

The theme of relevance to this article was the justifications given by researchers for undertaking mixed methods studies. When exploring justifications for using mixed methods research, the documents were used as the public face, and the interviews as the private face, of studies. Documentation was received for 81 studies and on reading the full documentation six studies were reclassified as not meeting the inclusion criteria, leaving 75 mixed methods studies.

Twenty-two researchers were approached for interview and 20 agreed to be interviewed. In this design only one data collection phase is used, during which a predominant method quantitative or qualitative nests or embeds the other less priority method qualitative or quantitative, respectively. This nesting may mean that the embedded method addresses a different question than the dominant method or seeks information from different levels. The data collected from the two methods are mixed during the analysis phase of the project.

This decision should be determined by the overall purpose of the research e. Take this short quiz to learn what are the best 3 methods to understand your audience and answer your research question s.

FoodRisc Resource Centre A resource centre for food risk and benefit communication. Evaluate your situation Understand your audience Create your message Media channels Monitor communications Public involvement.

When to use it? Mixed methods research is particularly suited: When one wants to validate or corroborate the results obtained from other methods. When one needs to use one method to inform another method. For instance, when little is known about a topic and it is necessary to first learn about what variables to study through qualitative research, and then study those variables with a large sample of individuals using quantitative research. When one wants to elaborate, clarify, or build on findings from other methods.

For instance, if a causal relationship has being established through experimental research but one wants to understand and explain the causal processes involved through qualitative research. When one wants to develop a theory about a phenomenon of interest and then test it. Usually, qualitative research is more suitable to build theory, while quantitative research provides a better way of testing theories.

When one wants to generalize findings from qualitative research. Advantages The use of mixed method research provides a number of advantages, namely: Provides strengths that offset the weaknesses of both quantitative and qualitative research.

For instance, quantitative research is weak in understanding the context or setting in which people behave, something that qualitative research makes up for. On the other hand, qualitative research is seen as deficient because of the potential for biased interpretations made by the researcher and the difficulty in generalizing findings to a large group.

Quantitative research does not have these weaknesses. Thus, by using both types of research, the strengths of each approach can make up for the weaknesses of the other. For example, a PCMH study could begin with a qualitative exploration through interviews with primary care providers to assess what constructs should be measured to best understand improved quality of care. From this exploration, an instrument could be developed using rigorous scale development procedures DeVellis, that is then tested with a sample.

In this way, researchers can use a mixed methods approach to develop and test a psychometric instrument that improves on existing measures. Use qualitative data to augment a quantitative outcomes study. An outcomes study, for example a randomized, controlled trial, with qualitative data collection and analysis added, is called an embedded design.

Within this type of an outcomes study, the researcher collects and analyzes both quantitative and qualitative data. The qualitative data can be incorporated into the study at the outset for example, to help design the intervention ; during the intervention for example, to explore how participants experience the PCMH model ; and after the intervention for example, to help explain the results. In this way, the qualitative data augment the outcomes study, which is a popular approach within implementation and dissemination research Palinkas, Aarons, Horwitz, et al.

Involve community-based stakeholders. A community-based participatory approach is an example of a multiphase design. This advanced mixed methods approach involves community participants in many quantitative and qualitative phases of research to bring about change Mertens, The multiple phases all address a common objective of assessing and refining PCMH models.

This design would involve primary care providers and staff, patients, and other providers and individuals in the community in the research process. Key stakeholders participate as co-researchers in a project, providing input about their needs, ways to address them, and ways to implement changes.

These five research designs apply mixed methods approaches to evaluations of PCMH models. The literature details their procedures, illustrates the flow of activities through the use of shorthand notation, and reflects on strengths and limitations.

Compares quantitative and qualitative data. Mixed methods are especially useful in understanding contradictions between quantitative results and qualitative findings. Fosters scholarly interaction. Such studies add breadth to multidisciplinary team research by encouraging the interaction of quantitative, qualitative, and mixed methods scholars.

Mixed methods research combines elements of quantitative research and qualitative research in order to answer your research question. Mixed methods can help you gain a more complete picture than a standalone quantitative or qualitative study, as it integrates benefits of both methods. Mixed methods research is often used in the behavioral, health, and social sciences, especially in multidisciplinary settings and complex situational or societal research.

Table of contents When to use mixed methods research Mixed methods research designs Advantages of mixed methods research Disadvantages of mixed methods research Frequently asked questions.

Mixed methods research may be the right choice if your research process suggests that quantitative or qualitative data alone will not sufficiently answer your research question.

There are several common reasons for using mixed methods research:. As you formulate your research question , try to directly address how qualitative and quantitative methods will be combined in your study. If your research question can be sufficiently answered via standalone quantitative or qualitative analysis, a mixed methods approach may not be the right fit.

But mixed methods might be a good choice if you want to meaningfully integrate both of these questions in one research study. For example, you could use a mixed methods design to investigate whether areas perceived as dangerous have high accident rates, or to explore why specific areas are more dangerous for cyclists than others. There are different types of mixed methods research designs.

The differences between them relate to the aim of the research, the timing of the data collection , and the importance given to each data type. In a convergent parallel design, you collect quantitative and qualitative data at the same time and analyze them separately. After both analyses are complete, compare your results to draw overall conclusions. When you finish your data collection and analysis, you then compare results and tie your findings together.

Embedded In an embedded design, you collect and analyze both types of data at the same time, but within a larger quantitative or qualitative design. One type of data is secondary to the other. This is a good approach to take if you have limited time or resources.

You can use an embedded design to strengthen or supplement your conclusions from the primary type of research design. In an explanatory sequential design, your quantitative data collection and analysis occurs first, followed by qualitative data collection and analysis.