Combining quantitative and qualitative methods

Combining quantitative and qualitative methods For many years qualitative and quantitative methods of research were seen as two distinct methods which could not be combined due to their differences. However, the combination of quantitative and qualitative methods has become widely advocated by researchers due to its pragmatism; as Douglas puts it: Since all research methods have costs and benefits, and since they differ greatly in their particular costs and benefits, a researcher generally finds it best to use some combination or mixture of methods. (1976:30) However, it is an imperative for any researcher to take into consideration the technicalities and complexities of combining research methods. This essay will argue that it is possible to combine quantitative and qualitative methods; furthermore, it is desirable. It is often said that two opposites usually attract and there is no divergence in this instance, even though it is said that the only similarities these two methodological positions share are many of the same characters in their names. This essay will begin by briefly explaining the two methods. It will secondly highlight the embedded methods argument and criticise it in order to justify the desirability of combining the two methods. This essay then aims to to dispel the common argument that combining the two methods is not desirable due to many researchers not having the relavent expertise. This essay will then analyse the purist criticisms of combining quantitative and qualitative methods before it presents the pragmatist p osition which highlights the desirability of combining qualitative and quantitative methods. This essay then argues that triangulation shows that it is both possible and desirable to combine the two methods, due to it contributing to the completeness and conformation of research. In conclusion this essay will argue that it is both desirable and possible to combine quantitative and qualitative methods and that mixed methods research has nearly won the paradigm wars due to its substance. Quantitative research methods tend to be ontologically foundationalist in that both natural and social phenomena are assumed to have an existence that is independent of the activities of the human observer (Blaikie, 2007: 13). Therefore, they believe in objectivity in research being possible. Research of this sort is usually epistemologically positivist, in that they believe that social science is analogous to the natural sciences. They look for causal explanations through the use of scientific laws in order to explain social phenomena thus developing explanatory, and indeed predictive, models. (Marsh and Furlong, 2002: 20). Examples of quantitative data are questionnaires, structured interviews and statistical analysis of official data. Whereas qualitative research methods tend to be ontologically anti-foundationalist in that what we regard as the external world is just appearances and has no independent existence apart from our thoughts (2007: 13). Therefore, the world is socially or discursively constructed and as a result objectivity in research is not possible. They usual encompass a non-positivist epistemology such as the interpretist tradition in which these researchers are concerned with understanding, not explanation, focuses on the meaning that actions have for agentsand offers their results as one interpretation of the relationship between the social phenomena studied. (2002: 21) Qualitative research usually works with smaller amounts of data unlike quantitative research. Some variants of qualitative research are focus groups, case studies and unstructured interviews. One of the main criticisms of combining qualitative and quantitative methods lies with the embedded methods argument that is posed by researchers who take a purist stance. They argue that quantitative and qualitative methods cannot be combined as this will compromise ones ontological and epistemological position. According to Marsh and Furlong your ontological and epistemological positions are like a skin not a sweater (2002: 17). Therefore, researchers cannot interchange between their adopted positions for different research projects as they reflect fundamental different approaches to what social science is and how we do it (2002: 21). They argue that the researchers ontological and epistemological positions affect all aspects of ones research. So for example, if one is ontologically foundationalist they cannot also argue people are able to socially construct certain aspects of life, such as gender. Or if you are epistemologically interpritivist you cannot use the natural sciences a s a precursor in the study of the social sciences. As shown above there certainly are differences amongst the two methods; however, does this mean it is undesirable to combine the two? It is very important for researchers to take into account their ontological and epistemological positions (as shown above they play an important role within research), although, researchers should not treat their ontological and epistemological positions as the most fundamental aspect for research. Combining the two methods is desirable, as one must not be overwhelmed by the higher philosophical debate, as many researchers have been in the past, because this makes you forget that as a researcher undertaking a project you wish to undertake the best research possible and in order to do this you must understand that each method has a very crucial role to play in furthering our grasp and knowledge of the research question. Therefore one must understand that Qualitative and quantitative research makes up a false dichotomy There are many right ways to approa ch research, not only one right way. (Newman et al cited in Teddie and Tashakkori, 2009:28) Therefore, this idea that the different research methods have fixed epistemological and ontological positions that cannot be compromised is very hard to sustain. It is hard to sustain because, as critical realists argue, one can see the world as being both ontologically foundationalist and anti-foundationalist, in that you could believe that the world exists and is independent to a certain extent as the knowledge about it is socially constructed. Also, epistemologically, yes it is important to take into account your epistemological stance; however, there are certain instances when it is necessary to look at the research question from a positivist stance and other instances when the research should be interpretivist. As Howe illustrates through the use of Kaplans story, were a drunken man searches under a lamp for his, which he had dropped a fair distance away. When asked why he was looking there and not where he dropped it, he said that the reason was because it was lighter where he was looking. Howe then argues that The incompatibility thesis, like the drunkards search, permits the lights to determine what is to be looked for and where. But why should paradigms determine the kind of work one may do with inquiry any more than the amount of illumination should determine where one may conduct a search? (Howe, 1988: 13). Whilst considering whether or not it is possible and desirable to combine quantitative and qualitative research, one has come across a common argument in many articles and books. This being, that many researchers, do not have the skills and training to carry out both quantitative and qualitative research (Bryman, 2008: 624). However, in my opinion this is understandable but ludicrous. Due to researchers in the past taking the position of either/or it is understandable that not all researchers have the necessary training to conduct such research, however, this is no excuse and it is time to take a more both-and perspective. It is almost like saying a goalkeeper that has learnt to save the ball on his left hand should not try and learn to use both hands even if it will improve his goalkeeping skills as this is how he has learnt to play. Therefore, this should not be used as an excuse, moreover, it should be more of an encouragement to overcome this challenge because as pragmatists argu e, as a researcher if you believe in this papers argument that combining the two methods are both desirable and possible then you as a researcher must strive to do whatever you can to produce the best possible research you can. Purists tend to emphasise the ontological, epistemological, and axiological (the role of values in inquiry) differences. This incompatibility thesis is well stated by Smith, who says: One approach takes a subject-object position on the relationship to subject matter; the other takes a subject-subject position. One separates facts and values, while the other sees them as inextricably mixed. One searches for laws, and the other seeks understanding. These positions do not seem compatible. (1983: 12) Therefore, according to these theorists it is neither possible nor desirable to combine qualitative and quantitative methods as you would only be dooming your research for failure due to the inherent differences between the methods. However, other researchers which come from a pragmatist background argue that this is not the case and the differences are exaggerated and overdrawn. Rather than being wed to a particular theoretical style and its most compatible method, one might instead combine methods that would encourage or even require integration of different theoretical perspectives to interpret the data. (Brewer Hunter, 1989: 74) Pragmatism thus is thus is the belief in the ability to combine qualitative and quantitative methods without compromising your ontological and epistemological positions. Johnson and Onwuegbuzie define the main characteristics of pragmatism as follows. It recognises the existence of this real world that positivists talk about but it also recognises this world which relies on socially and discursively constructed phenomena. For example, take gender again, it argues that yes gender does exist in that there are men and there are women, however, through discourse we have constructed gender in that we have attached further meaning to them (men are not meant to cry but instead should act manly, whilst women should be emotional and weak). It views knowledge as being both constructed and based on the reality of the world we experience and live in. It views theories instrumentally. It endorses empiricism as the way to find out what works. It endorses eclecticism and pluralism in that one can f ind different and conflicting perspectives useful to enhance ones understanding of people and the world. Also, current truth, meaning and knowledge are changing over time, therefore, one should treat research as only provisional truth at it could change in a matter of time (2004: 18). This is a very realistic way of overcoming many of the criticisms of purists when combining methods even though it has some criticism itself. When put under the microscope it has been deemed to be very practical. This pragmatist position has highlighted the desirability of combining qualitative and quantitative methods by unravelling the purist incompatibility thesis through the rejection of the historical dualisms commonly associated with these methods; and this essay will go on to proving that it is also possible to combine these methods. One way in which researchers can successfully combine qualitative and quantitative methods is through triangulation. Even though there are many methods of combining qualitative and quantitative methods, such as, completeness, offset, process. This essay will focus on triangulation due to the space and time limitations. The early use of the term triangulation was not found in social science but instead, navigation and surveying. This term was used to describe when different bearings are taken, in order to be lead to a specific physical location, however, the second bearing here was not used to check the first bearing but instead they work together in order to indentify that specific location(Brannen, 2005:12). Denzin distinguished between the triangulation within methods and the triangulation between methods. Although, this essay will concentrate on the triangulation between methods, it is important to note that the triangulation within methods is desirable if need be, however, it doe s not solve any of the fundamental problems inherited by single method research. The methodological triangulation of Denzin(1978) refers to the combination of multiple methods [as] no method alone can adequately treat all problems of discovery and testing.'(Mouton and Marais, 1996: 2006). Johnson and Onwuegbuzie take the term to mean, seeking convergence and corroboration of results from different methods and designs studying the same phenomenon (2004: 22). For Jick it is largely a vehicle for cross validation when two or more distinct methods are found to be congruent and yield comparable data. (1979: 602). It is already clear that the term triangulation has a plurality of meanings varying from researcher to researcher. However, the core principles of triangulation aim to increase the validity of studies, by overcoming the inherent biases and limitations of either of the methods through using two or more methods which lead to the same findings. Therefore, if someone was conducting a study to investigate the link between age and who you vote for, they should not only look at the statistics but also question people on why they voted the way they have, because there could be reasons such as tactical voting, were for example someone only voted Labour because they did not want the Conservatives to get elected and if the situation was different they would have ideally voted for the Liberal Democrats. The use of the two different methods can help you falsify and understand your results in much more depth than you would by just using the one method. Jick (1979) conducted a study of anxiety and job insecurity of employees during a merger. This study used data from, co-worker observations, interviews, questionnaires and company archival records. The use of the different sources of data allowed Jick to see different perspectives on the situations effects on the employees. Jick had also found that when the use of the different methods did not corroborate each other it led to him seeking explanations for divergent results [and as a result], the researcher may uncover unexpected results or unseen contextual factors (1979: 608). Jicks study shows that combining quantitative and qualitative methods through triangulation can lead to better research as an implication of the increased validity and sometimes vigour it contributes to the study in question. However, it is important to understand that the two methods should not be combined for the sake of it or just because a researcher believes that, more is good, as in many instances this is not the case. Therefore, researchers must make sure that they only combine research when the conditions are right. In conclusion, triangulation has not only shown that it is desirable to combine quantitative and qualitative methods, but it has also shown that it is possible to combine the two methods , due to it contributing to the completeness and conformation of research. One only has to look at the shifting of the so called paradigm wars (Oakley, 1999) in order to see that it is both possible and desirable to combine quantitative and qualitative methods. Since the beginning of this so called war the proponents of both quantitative and qualitative methods have criticised each others methods and defended their own. The lack of a clear winner was one of the main reasons the combination of the two methods became so popular in the past and now the mixed methods approach has become very popular. This essay has shown that it is both possible and desirable to combine the methods and The growing popularity of mixed methods research would seem to signal the end of the paradigm wars (2008: 625). Even though mixed method research has many difficulties and criticisms itself, I believe that its advantages outweigh its disadvantages by far, as it adds breadth and depth to the analysis of the research. As Mingers correctly points out, the attractiveness of multimeth od research, in terms of the richness and increased validity of the results, will work in its favour in the long run (2003: 246). Both this richness and validity talked about by many researchers such as Mingers, is a compelling argument for the combination of quantitative and qualitative research and this essay has shown that it is possible to combine the two methods through the use of triangulation. This essay began by briefly explaining the two methods. It then went on to highlight the embedded methods argument before criticising it for not being sustainable. This essay then dismissed the common argument that combining the two methods is not desirable due to many researchers not having the relevant expertise by arguing that due to the desirability and practicality of mixed methods approaches researcher should find a way to mix the two methods in order to undertake better research when necessary. This essay then analysed the purist criticisms of combining quantitative and qualitative methods before it presented the pragmatist position which highlighted the desirability of combining qualitative and quantitative methods. This essay then argued that triangulation shows that it is both possible and desirable to combine the two methods, due to it contributing to the completeness and conformation of research. This essay concluded by arguing that it is both desirable and possible to co mbine quantitative and qualitative methods and that mixed methods research has nearly won the paradigm wars. Bibliography Blaikie, Norman, (2007) Approaches to Social Enquiry, Polity Press: Cambridge Brewer, J., and Hunter, A, (1989) Multimethod research: A synthesis of styles, Sage: California. Bryman, Alan (2008) Social Research Methods, Oxford University Press: New York Creswell, J. W. (1995). Research Design: Qualitative and quantitative approaches. Sage: Thousand Oaks Douglas, Jack D. (1976) Investigative Social Research, Sage: Beverley Hills Denzin, N. K (1978) The research act: A theoretical introduction to sociological methods, McGraw-Hill: New York Greenberg, J. and R. Folger (1988) Controversial issues in social research methods. Springer-Verlag: New York Guba, G. and E. Lincoln, (1994) Competing Paradigms in qualitative research, In N. K. Denzin and Y. S. Lincoln (Eds) Handbook of Qualitative Research (p105-117), Sage: Thousand Oaks Howe, Kenneth R. (1988). Against the quantitative-qualitative incompatibility thesis (or dogmas die hard). Educational researcher, Vol. 17, p.10-16. Marsh, David and Furlong, Paul, (2002) Ontology and Epistemology in Political Science in Marsh, David and Stoker, Gerry, Theory and Methods in Political Science, (MacMillan: Basingstoke), pp. 17-41 Mingers, John, (2003) The paucity of multimethod research: a review of the information systems literature, Info Systems Journal, Vol. 13, p. 233-249 Mouton, Johann and Marais HC, (1996) Basic Concepts: in the methodology of the social sciences, HSRC Publishers: Pretoria Jick, Todd D. (1979), Mixing Qualitative and Quantitative Methods: Triangulation in Action, Administrative Science Quarterly, Vol. 24, p. 602-611 Jick, Todd D. (1985). Mixing qualitative and quantitative methods: Triangulation in action. In Van Mannen (Ed.) Qualitative methodology (p135-148). Sage Publications: Beverly Hills Johnson, Burke R. And Onwuegbuzie, Anthony J. (2004), Mixed Methods Research: A Research Paradigm Whose Time Has Come, Educational Researcher, Vol. 33, p. 14-26 Newman et al cited in Teddie, Charles and Tashakkori, Abbas, (2009), Foundations of Mixed Methods Research: Integrating Quantitative and Qualitative Approaches in the Social and Behavioral Sciences, Sage Publications: California Oakley, Ann (1999), Paradigm wars: some thoughts on a personal and public trajectory, International Journal of social research methodology, Vol. 2, p. 247-254 Brannen, Julia, Mixed Methods Research: A discussion paper, NCRM Methods review papers, ESRC, Institute of Eduation, University of London Smith, John K. (1983) Quantitative versus qualitative research: An attempt to clarify the issue Educational Researcher, Vol.12, p. 6-13.