How the Choice of Research Interacts with the Choice of Theories to be Studied
How the Choice 1How the Choice of Research Methods Interacts with the Choice of Theories to be Studied Edgardo Donovan RES 620 – Dr. Wenli Wang Module 5 – Case Analysis Monday, December 19, 2011
How the Choice 2 How the Choice of Research Methods Interacts with the Choice of Theories to be Studied Research should not be confined with methodology or it may constrict scope of efforts.Past methods should be point of departure but eventually a pluralistic approach should beadopted. Rather than advocating a single paradigm, be it interpretive or positivism or even aplurality of paradigms within the discipline, research result would be more reliable and richer ifcombined together (Mingers 2001, p. 240). There are a variety of constraints and objectives that a researcher must consider when inthe process of choosing the right research model. Some of the challenges encountered whileattempting to deliver high quality research may be related to constraints on time, funding, humanresources, and research skills (Wang 2011, p. 2). At the same time, successful research shouldstrive to deliver unique contributions. One must gain a deep understanding foundational theoriesare already been paved and research norms already established in the field while infusing one’sbackground and experiences to provide unique insights (Wang 2011, p. 7). A critical portion ofany research endeavor revolves around data collection and analysis where one must strive tomake the research results as “generalizable” as possible while large enough to have significantpower (Wang 2011, p. 12). Finally, the completed research publication must have strongemphasis on relevance and rigor. The above two aspects must be successfully operationalizedthrough crisp research questions, coherent body of theory, clear modeling, consistent level ofanalysis, and comprehensive data analysis (Wang 2011, p. 1).
How the Choice 3 Often, divergent findings from research targeting the same variables may be a function ofresearch methods that primarily focus from the macro to the micro (group vs. individualistic) andvice versa. For example, Bradbury and Lichtenstein (2000) build a connection betweenBourdieu’s relational method and Schein’s theory of organizational culture, indicating the powerof Bourdieu’s method in revealing the implicit assumptions of and interdependencies betweendifferent forms of capital and social space. However, Bourdieus model overlooks divergentways that individuals choose their social positions and social field in which positions are taken islargely structured by overarching macro influences. If a researcher focuses too much on methods, he or she may formulate researchquestions based on methodology, or may choose to study trivial questions that can be studiedusing a fashionable technique. Clearly, formulation of research questions should be theory-driven or problem-driven rather than technique-driven. Given a theory-based or problem-basedquestion, one then determines a research design and method of analysis that will provide the bestanswer. Such an approach might or might not involve use of a sophisticated quantitativetechnique. We sometimes forget that important research is not necessarily characterized by theapplication of sophisticated or complex statistical techniques. In fact, important research mightwell involve very simple approaches, including case studies or qualitative analyses. Researchersshould avoid method-driven research, as well as to avoid biases against simple designs andanalyses and in favor of complex analyses and fashionable methods. We shouldn’t be impressedby flashy analyses that address trivial questions. Rather, we should place highest value ontheory-driven and problem-driven studies that address important questions and that use
How the Choice 4sophisticated quantitative knowledge and insight to choose the best methodological approach(MacCallum 1998, p. 38). Using Internet studies as an a example one can see how it is very easy to get divergingviews within the same study if not careful in setting up a rigorous model involving varying formsof structural equation modeling, factor analysis, and measurement. It is particularly difficult toconduct a longitudinal study in that there can be many consistencies when attempting to cullgood data from participants over long periods of time. If proper factor analysis is not conductedit is possible that confusion related to macro or micro influences may occur. For example, onemay find it difficult to answer the question related to whether spending more time on the Internetcommunicating via email with friends is more socially inclusive than spending time at the barwith friends. Whenever possible a model that is parsimonious and substantively meaningful with regardto its structure and the resulting parameter estimates, and which fits empirical data adequatelywell. If we achieve that goal, it would be wonderful if we could then believe that we haveidentified the true pattern of relationships among our variables and that we could makeinterpretations, draw conclusions, and take action on that basis. But that is never the case. Infact, such an outcome yields a model that can be viewed only as providing one plausible andapproximate explanation of the real-world phenomena we are trying to explain. There willalmost certainly exist other models that fit our data as well or better, and some of thesealternatives may be sufficiently parsimonious and as meaningful as, or even more meaningfulthan, the original model. None of these models represents the “true model,” which doesn’t exist.Thus, we must always temper and moderate our conclusions by taking these principles into
How the Choice 5account. We must recognize the limitations of our techniques and not reach beyond thoselimitations to grasp at unjustified interpretations (MacCallum 1998, p. 41). A methodology for choosing the right model to for research is unique and can only bedone on a case by case basis. One way to take this issue into account in assessment of model fitis through the use of the ECVI (expected cross-validation index). The ECVI estimates the degreeto which a solution obtained from the sample at hand would generalize to the population. Use ofthe ECVI under varying levels of sample size will show that simpler models are preferred whensample size is small, whereas more complex models can be supported when sample size is large.This index is not useful for evaluation of single models because it has no inherent referencepoint, but is very useful for comparison of alternative models. Confidence intervals are availablefor ECVI. Use of indexes such as RMSEA and ECVI can help the investigator identify the bestmodel from among a set of alternatives, rather than attempt to determine the quality of a singlemodel (MacCallum 1998, p. 44). Research should not be confined with methodology or it may constrict scope of efforts.Past methods should be point of departure but eventually a pluralistic approach should beadopted. Rather than advocating a single paradigm, be it interpretive or positivism or even aplurality of paradigms within the discipline, research result would be more reliable and richer ifcombined together (Mingers 2001, p. 240).
How the Choice 6 BibliographyComer, Douglas (2005) Ways To Measure Research. Working Paper, Purdue University.Retrieved May 19, 2008 from: http://www.cs.purdue.edu/homes/dec/essay.research.measure.htmlBradbury, Hilary and Lichtenstein, Benyamin (2000) Relationality in organizational research:Exploring The Space Between. Organization Science. 11(5):551-580Kiesler, Sara, Kraut, Robert and others (2002) Internet evolution and social impact. IT andSociety. 1(1):120-134Kraut, Robert and others (1998) Internet paradox: a social technology that reduces socialinvolvement and psychological well-being? American Psychologist 53(9):1017–1031Kraut, Robert, Kiesler, Sara, Boneva, Bonka, Cummings, Jonathon, Helgeson, Vicki, andCrawford, Anne (2001) Internet paradox revisited. Journal of Social Issues.MacCallum, Robert (1998) Commentary on quantitative methods in i-o research. TheIndustrial-Organizational Psychologist 35(4)Mingers, John (2001) Combining IS research methods: towards a pluralist methodology.Information Systems Research. 12(3):240-260Shackman, Joshua (2011) Deal breakers for dissertation at TUI. Trident University
How the Choice 7Wang, Wenli (2011) Integration of research question, theory, and methodology. TridentUniversityWhittaker, Steve (2005) Supporting Collaborative Task Management in E-mail. Human-Computer Interaction, 2005, Vol. 20, No. 1&2, Pages 49-88