Quantitative, Qualitative or Both? Combining Methods in Linguistic Research (Jo Angouri)

There are three kind of linguistics research. They are quantitative, qualitative, and combination of qualitative and quantitative. To use these kind of research we have to understand the definition of them. The summary of this chapter will explain when we use of each type of research. It is related to triangulation method to valid the research.

Triangulation is the application and combination of more than one research perspective in the study of the same phenomenon. Triangulation is also typically perceived to be a strategy for improving the validity of research or evaluation findings. Dezin’s (1970:472) early work indicated that there is more than one type of triangulation (p: 34)

Triangulation is often one of the key reasons for undertaking mixed method research. According to the typology of mixed methods design suggested by Greene et al. (1989) – but also more recently by (Bryman, 2006) – the term stands for convergence of findings and corroboration of research results. According this view, the expectation is that different datasets or different methodologies will lead to similar result and hence allow for ‘confident interpretation’ (e.g. Lyons, 2000: 280) of the findings and strengthen the researcher’s conclusions. As such the term is also widely associated with the concept of credibility of research findings. A problem associated with this approach is the assumption that data collected using different methods can necessarily be compared or contrasted in order to answer the same set of research question. This view assumes that there is one single objective ‘reality’ or ‘truth’ – not only a problematic assumption, but also, as argued by Harden and Thomas (2005) one that ignores that data from different sources often reveal conflicting realities.

Researchers undertake mixed methods research in order to answer their specific research questions without positioning themselves to either qualitative, quantitative, or mixed methods paradigms (Harden and Thomas, 2005). Interestingly surveys (quantitative) and interviews (qualitative) seem to be the most dominant method used by researchers. This is also a popular method of triangulation that is widely used. However, in practice, this method may require more resources in order to evaluate the program using different methods. Likewise, it will require more time to analyze the data/information yielded by the different methods.

Given the multifaceted nature of research on discourse, it has been argued that collecting data from different source in an iterative way is an appropriate way to address research question in this area (Beaufort, 2000). While discourse studies are often seen as ‘by nature’ qualitative, being largely based on naturally occurring ‘real life’ data, recent work (e.g. Holmes and Marra, 2002) has shown how quantitative and qualitative paradigms can be combined for a better understanding of the interactants’ norms and practices in discourse (p: 36).

There are many examples of mixed method designs in workplace discourse studies. Jorgensen’s 2008 work on governmental discourse, makes a strong case for combining methodologies in genre analysis, by using interviews, questionnaires and an extensive corpus of written documents. A case for integrating the two paradigms is also made by Holmes and Marra (2002) in a study on the functions of humour in communities of practice within different New Zealand workplaces. This study is clear example of how quantitative and qualitative components can be combined to address a research topic that many would associate solely with qualitative research. The quantitative data in this study reveal different frequencies of humour instances as well as humour types. The researchers distinguish between supportive and congestive humour and also classify humour instances according to style (collaborative or competitive). At the same time the closer qualitative analysis of discourse data shows how ‘humour is used’ in the workplaces they study and the way the employees ‘do humour’ (Holmes and Marra, 2002:1702) to achieve their interactional goals.

Overall, mixed methods research can and does cross – displinary boundaries and overcome limitations that have been associated with mono – dimensional approaches to the study of complex phenomena and research sites (such as the workplace). As we have seen, mixed methods research also helps in making the research relevant to wider audiences, but also in avoiding orthodoxies such as those imposed by mono – dimensional, purist approaches to researches that ‘are potentially damaging to the spirit of enquiry’ (Holmes and Meyerhoff, 2003: 15) (p: 41)

Qualitative and quantitative methods can be mixed in one research. However, it won’t guarantee that the result of the research can always be better. When we want to mix both of those methods, we have to use the triangulation method. This triangulation method is aimed to prove the validity of the research. In brief, we have to be focus and consistent on the method that we are using in conducting the research.

Source: Angouri, Jo. 2010. Quantitative, Qualitative or Both? Combining Methods in Linguistic Research. In Litosseliti, Lia. 2010. Research Methods in Linguistics. New York: Continnum International Publishing Group.