Ellis and Levy (2008) argue that a well structured and research-worthy problem statement is the mainstay of a research. The problem statement is grounded in the research topic, questions, goals, methodology, data gathering and analysis, and conclusions. While these topics are important, the data gathering approach is the deciding factor for the research validity and reliability. Specifically, qualitative and quantitative methods define the quality of research, and the research approach defines the methods and helps to derive the theory. Two main research approaches available are inductive and deductive. Inductive approach, also called a top-down approach starts with a series of hypothesis that are tested by gathering data and using quantitative methods. Deductive or bottoms-up approach examines data and use qualitative methods to form observations and form conclusions. Both these approaches help in formation and development of a theory that can be generalized.
Harlow (2009) agrees with the benefits of quantitative and qualitative research. However, she argues that the next stage is the development of case studies that affirm or develop theories with a practical approach. Her assumption is that qualitative and quantitative methods generate numbers and these are analyzed with statistical methods that prove or disprove a hypothesis or a theory. Case studies on the other hand, verify or disprove the findings from the two approaches. One main issue is that the two approaches are broad based and they can be applied to a certain group of events. It is possible that when a special event s examined, it may not follow the theory, mainly because of the generalizations formed in the research method differ from the actual events in the case study. However, this does not mean that theory development or the research method is flawed and not inter-related. When the research methods and data collection methods are applied correctly, they help to form theories.
Hussein (2015) takes a different view and argues that the use of triangulation for mixed methods, where qualitative and quantitative methods are used, creates a richer and in-depth analysis from multiple perspectives. However, the triangulation is subject to interpretive bias since the nature of data gathered data sources, and analysis methods are epistemologically and ontologically different. The researcher needs to clarify how each variable or data set gathered to qualitative methods is linked to quantitative method and how these are related to the hypothesis and theory formation. If these efforts are not taken, then theory formation and justification is loose and repeatability is poor. However, many researchers fall in this trap and the results are questionable.
Mertens (2014) takes a different perspective when he speaks of qualitative and quantitative methods. He argues that these two methods are vast, extensive, and have various sub categories, with each having a different approach and objective. Some qualitative methods are ethnographic studies, phenomenological research, grounded theory, participatory research, etc, while categories of quantitative methods are primary and secondary research with surveys, semi-structured interviews, and literature reviews. The author argues that in many instances, the research question is narrow, focused on a specific event, and the research is directed to answer the question. It may not be possible or realistic to develop a theory from such a research. However, the researcher can use a sound literature review to develop a base for a theory and attempt to describe the findings as a theory.
Ragin (2014) disagrees with the arguments by other authors. He is of the opinion that some subjects are suitable for theory development while others are useful to explain a specific event. Speaking of multivariate statistical techniques, the authors argues that statistical data is narrow and cannot be used to hypothesize on complex patterns, required for theory formation in the field of economics, science, business management, and other disciplines. These methods are suitable to develop theory in subjects such as sociology, philosophy, and other related sciences, when the sample size is large. Unfortunately, researchers are in a hurry to generalize from a few studies and prescribe sweeping theories that may have common characteristics with a number of events, but, which are unsuitable to explain specific phenomena. Some authors develop research models rather than theories with multiple conditional inputs and outputs.
Allwood (2012) rejects the commonly accepted differences between qualitative and quantitative research methods, leading to serious lapses in research. He points out that heterogeneity of multiple stand-points on several issues such as causal analysis and quantification, results in unstable research. A suggestive overlap is formed between the two methods, resulting in poor differentiation between the two methods. As a result, theory formed by using one or both methods can result in errors. Focus of the researcher is on proving justification of the methods, how they produce different sets of data, and the manner in which the findings can be triangulated. The result is an overemphasis on merging findings from the two approaches, resulting in an improper application of findings, which are difficult to merge into a set of cohesive observations. This is especially true when the researches attempts to merge findings from survey with observations from statistical data and results. Needless to say, theory formed from these observations has low validity and reliability.
Venkatesh, Brown and Bala (2013) support the use of mixed methods research, where quantitative and qualitative methods are integrated for research in information systems. To develop robust theory, the authors suggest that the two methods must be grounded in theory with common factors in observations, meta-inferences with substantive theory must be developed, and the quality of meta-inferences with validation of mixed methods research must be well founded. Emergent theory is possible when these processes are followed. It is possible to build insights into various events and phenomena that cannot be fully explained by using one of the methods. Quality of secondary research, experience and expertise of respondents, and framing of research questions the research framework, and the survey instrument must be robust.
We can do it today.
Halevi, Lewis and Memon (2013) speak of research in cyber security and qualitative, quantitative methods. The authors indicate that unlike other topics, cyber security involves constructs from several disciplines such as behavioral sciences, criminal psychology, terrorism, thrill seeking, profit and economic motives, and several others. The research question needs to focus on one of these disciplines, since covering all these issues would make the research very complex. In addition, cyber security has many related and independent variables. It would be difficult to co-relate all these variables and derive common theory that combines all the variables. Any emergent theory would essentially focus on one of the disciplines. This observation is important considering that the proposed research is on cyber security.
- Allwood, C. M. (2012). The distinction between qualitative and quantitative research methods is problematic. Quality & Quantity, 46(5), 1417-1429.
- Ellis, T. J. & Levy, Y. (2008). Framework of Problem-Based Research: A Guide for Novice Researchers on the Development of a Research-Worthy Problem. Informing Science: the International Journal of an Emerging Transdiscipline, 11, pp. 17-33.
- Halevi, T., Lewis, J., & Memon, N. (2013). A pilot study of cyber security and privacy related behavior and personality traits. In Proceedings of the 22nd International Conference on World Wide Web, Rio de Janeiro, Brazil, May 13-17, pp. 737-744.
- Harlow, E. (2009). Contribution theoretical. Encyclopedia of Case Study Research. Thousand Oaks, CA: Sage.
- Hussein, A. (2015). The use of triangulation in social sciences research: Can qualitative and quantitative methods be combined? Journal of Comparative Social Work, 4(1).
- Mertens, D. M. (2014). Research and evaluation in education and psychology: Integrating diversity with quantitative, qualitative, and mixed methods. Sage publications: NY.
- Ragin, C. C. (2014). The comparative method: Moving beyond qualitative and quantitative strategies. University of California Press, CA.
- Venkatesh, V., Brown, S. A., & Bala, H. (2013). Bridging the qualitative-quantitative divide: Guidelines for conducting mixed methods research in information systems. MIS quarterly, 37(1), pp.21-54.