What research approach has specific boundaries that can be both qualitative and quantitative?

Research on mixed methods has been widely used in health care research for various reasons. The integration of qualitative and quantitative approaches is an interesting question and continues to be one of the many debates (Bryman, 2004; Morgan, 2007; Onwuegbuzie and Leech, 2005). In particular, the various hypotheses and epistemological and ontological paradigms associated with qualitative and quantitative research had a major influence on discussions on the question of whether the integration of the two is possible, and even less desirable (Morgan, 2007; Sale et al., 2002). 

Supporters of research on mixed methods suggest that the vision of purists, that quantitative and qualitative approaches cannot be merged, constitutes a threat to the progress of science (onwuegbuzie and Leech, 2005) and that if the commitments Epistemological and ontological can be associated with certain research methods, connections are not necessary deterministic (Bryman, 2004). 

Rather than pursuing these debates in this article, we aim to explore the approaches used to integrate qualitative and quantitative data into health care research. Consequently, this article focuses on practical issues in the management of mixed methods and the need to develop a rigorous framework to design and interpret mixed methods to advance the field. 

In this article, we will try to provide advice for research on intermediate methods interested in means of combining qualitative and quantitative methods. The concept of mixing methods was introduced for the first time by Jick (1979), as a means of seeking convergence through qualitative and quantitative methods within social science research (Creswell, 2003). 

It has been advanced that the search for mixed methods can be particularly useful in health care research because only a range of perspectives can do justice to the complexity of the phenomena studied (Clarke and Yaros, 1988; Foss and Ellefsen, 2002; Steckler et al., 1992). By combining qualitative and quantitative results, a global or negotiated report of the results may be forged, not possible using a singular approach (Bryman, 2007). 

Mixed methods can also help highlight the similarities and differences between specific aspects of a phenomenon (Bernardi et al., 2007). The interest and expansion of the use of mixed methods have been recently fueled by pragmatic problems: growing demand for profitable research and the remoteness of research theoretically motivated to research that meets the needs of decision-makers and practitioners and growth in competition for research financing (Brannen, 2009; O'Cathain et al., 2007). 

Tashakkori and Creswell (2007) largely define research on mixed methods as "research in which the investigator collects and analyzes data, integrates results and draws inferences using both qualitative and quantitative approaches" (2007: 3). In any study of mixed methods, the aim of mixing qualitative and quantitative methods should be clear to determine how analytical techniques relate to each other and how, if necessary, the results must be integrated (O'Cathain et al ., 2008; Onwuegbuzie and Teddlie, 2003). 

It was argued that a characteristic of really mixed methods is that which implies the integration of qualitative and quantitative results at a certain stage of the research process, whether During the collection, analysis, or the research phase of research (Kroll and Neri, 2009). An example of this is found in mixed methods that use a simultaneous data analysis approach, in which each data set is integrated during the analytical phase to provide a complete image developed from the two data sets after the qualified or quantified data (that is, where the two of the data forms have been converted into qualitative or quantitative data so that they can be easily merged) (onwuegbuzie and Teddlie, 2003).

Other analytical approaches that include; Analysis of parallel data, in which the collection and analysis of both data sets are carried out separately and the findings are not compared or consolidated until the interpretation stage, and finally the analysis of sequential data, in which the Data are analyzed in a particular sequence with the purpose of informing, instead of being integrated with the use or findings of the other method (Onwuegbuzie and Teddlie, 2003). 

An example of sequential data analysis could be where quantitative findings are intended to lead to a theoretical sampling in a deep qualitative investigation or where qualitative data is used to generate elements for the development of quantitative measures. When qualitative and quantitative methods are mixed in a single study, one method generally has priority over the other. 

In such cases, the objective of the study, the justification for using mixed methods, and the weighting of each method determine if the empirical findings will be integrated. This is less challenging in the studies of sequential mixed methods where an approach clearly informs the other, however, the orientation to combine qualitative and quantitative data of equal weight, for example, in studies of mixed methods with current, is much less clear ( Foss and Ellefsen, 2002). 

This becomes even more challenging by a common defect that is insufficient and inexplicitly identifying the relationships between epistemological and methodological concepts in a particular study and the theoretical propositions on the nature of phenomena under investigation (Kelle, 2001). An approach to combine different data of equal weight and facilitates the clear identification of the links between the different levels of theory, epistemology and methodology could be to frame triangulation as a "methodological metaphor", as Erzberger and Kelle (2003) argue. 

This can help; Describe the logical relationships between qualitative and quantitative findings and theoretical concepts in a study; Demonstrate the way in which qualitative and quantitative data can be combined to facilitate an improved understanding of particular phenomena; And can also be used to help generate a new theory (Erzberger and Kelle, 2003) (see Fig. 1). The points of the triangle represent theoretical propositions and empirical findings from qualitative and quantitative data, while the sides of the triangle represent the logical relationships between these propositions and findings.

Download

Reference

Östlund, U., Kidd, L., Wengström, Y., & Rowa-Dewar, N. (2011). Combining qualitative and quantitative research within mixed method research designs: a methodological review. International journal of nursing studies, 48(3), 369-383.

Both qualitative and quantitative research are indispensable tools in a researcher’s toolbox. Cint provides a platform for conducting quantitative research via online surveys – a solution that can be quite useful for augmenting qualitative research.

First, it’s important to understand the difference between qualitative and quantitative research. Qualitative research is primarily exploratory in nature, and helps a researcher better understand motivations, needs, processes, and rationale for behaviors (among other things). It provides deep insights into a situation, and helps form ideas or hypotheses for potential quantitative research.

Quantitative research, like online surveys, tends to be more numbers-focused and can help to assess hypotheses from qualitative research. Adding a quantitative approach to qualitative research can provide a more holistic (and quantifiable) view of the subject matter you are researching.

Conversely, qualitative research can be beneficial when designing a quantitative research project, helping in the following ways:

• Learning about the consideration process – that is, how a customer thinks about or uses a product or service, and the context for a purchase.
• Hearing a customer’s language – this helps when writing questions. Speaking in a customer’s language (rather than the internal language of a corporation) helps elicit the best answers leading to the best insights.
• Understanding the holistic customer experience – hearing descriptions of the logical sequence of events helps to frame the quant survey in a way that will make sense to the consumer. This also helps hone-in on the right customer targets, and the timeframes to be studied.

Considerations when moving from qual to quant research

Once qualitative research has been completed, you can use these findings to inform your quantitative research. Some considerations for migrating to quantitative research include the following:

Which targets should be interviewed, and how does that impact my sample design?

The fundamentals of any quant survey involve identifying the right sample design to fit the research objectives. The key question when migrating from qualitative to quantitative research is: “Did the qual interviews uncover insights that change the incoming assumptions?” For example, did we learn we should expand the population under study, possibly including purchase influencers rather than only interviewing decision makers. If so, expanding the scope of the sample design to include new targets can prove beneficial.

How can I use the quant research to obtain the deepest insights, maybe going beyond the original research objectives?

If the scope of the sample design has been expanded, creating quotas with statistically readable base sizes for any new targets is desirable – which can lead to insights above and beyond the original objectives. Regardless of the target audience(s) to be studied, researchers should balance statistical reliability with sample budget to obtain the best outcome for all constituents of the research.

If further qualitative findings are needed, how can I obtain those through the quant survey?

While traditional open-ends provide opportunities to obtain qualitative data, they do lack the richness gained through one-on-one dialogue. By embedding an interactive feature into a quant survey to further query respondents, open-ends can become more valuable. There are a number of companies today offering capabilities to engage an interviewer in real-time from a quant survey, or to probe through a chat-bot. In both cases, these interactions lead to the best of both worlds – deeper qualitative responses at quantitative research sample sizes.

Are there hybrid qual/quant platforms that lend themselves to exploration similar to traditional qual?

In a similar manner, researchers today have created a variety of methods and services that merge the depth of qualitative interviewing with the breadth of a quant survey. Some of these services engage hundreds of people to vote up or down the answers of others to achieve a consensus, while others are moderated more like a focus group but with a more readable sample size. In all cases, researchers should explore and consider some of these options for merging qual with quant, or creatively fusing the best of both into your own methodology.

Can quant interviewing replace any future qualitative research?

Historically quantitative research has been more expensive than qualitative. But today the rapid deployment of online surveys with reasonably priced sample can deliver insights fast and cheaper with greater statistical reliability than some qualitative projects. If the intent of some research was a qualitative deep-dive into certain subject matter (for example, the different uses of a household cleaning product), it could make more sense to use a qual/quant hybrid approach or to integrate a real-time chat tool into an online survey. In that way, qualitative depth is obtained along with the prevalence of the different product uses along with statistical reliability.

Best uses of qualitative and quantitative research methods

Quantitative and qualitative research are complementary methods that work well together to provide insights that are both deep and wide. Regardless of the research objectives, now more than ever researchers have options and countless qual/quant tools to design projects that deliver more actionable insight.

Contact our team to learn more about Cint’s survey solutions for quantitative research!

If you are interested in adding a quantitative component to your qualitative research, Cint’s team of experts can help guide you through the process. Contact the Cint team for more information.