Case based Methods and Statistical methods: Complementarity

Home Forums Methodspace discussion Case based Methods and Statistical methods: Complementarity

Viewing 9 posts - 1 through 9 (of 9 total)
  • Author
  • #820

    I am keen on the complementarity that exist between case based methods and statistical methods. I have read the book chapter by Prof Bent Flyvbjerg and I am busy with an article, which demands a better understanding of the issues. I am working on construction research, which appears to favour statistical methods. Please kindly refer me to additional information in this regard


    It depends on the field of research and way of integrating them. Many different ways of combining qualitative and quantitative research are discussed in

    Creswell, John W. and Vicki L. Plano Clark (2011): Designing and Conducting Mixed Methods Research. Los Angeles: SAGE Publications.

    More focused discussions on combining regression and case studies can be found in

    Lieberman, Evan S. (2005): Nested Analysis as a Mixed-Method Strategy for Comparative Research. American Political Science Review 99 (3): 435-452.
    Rohlfing, Ingo (2008): What You See and What You Get: Pitfalls and Principles of Nested Analysis in Comparative Research. Comparative Political Studies 41 (11): 1492-1514.
    Seawright, Jason and John Gerring (2008): Case Selection Techniques in Case Study Research: A Menu of Qualitative and Quantitative Options. Political Research Quarterly 61 (2): 294-308.

    Stephen Gorard

    More realistic approaches of combining appear in:

    Gorard, S., with Taylor, C. (2004) Combining methods in educational and social research, London: Open University Press

    where examples include logistic regression leading to case studies – entitlement ‘new political arithmetic’ 


    In what sense are the ways discussed in the references I mentioned less realistic?

    Stephen Gorard

    Usual issue of conflating research design with methods of data collection and analysis. Always be suspicious of those wanting to tell others how to do research (or indeed any skilled activity) without having done it themselves. Leads to lack of realism. 


    Any research, be it on substance or methods, should be judged based on criteria independent of the person who did the research. If recommendations make sense based on these criteria (internal coherence etc.), why should it matter the researcher haven’t used them himself/herself? It doesn’t matter.

    Stephen Gorard

    We are not talking about reporting research (on anything). My comment is about those feeling free with advice about things they have never tried. If someone ‘did the research’, to use your phrase, my comment would not apply. I said ‘without having done it themselves’. I would have thought the difference was clear. 


    Dear Ingo,

    Many thanks for these references. I have read the work of Creswell and Plano Clark and I shall now look at the other references and then reflect on their implications in construction research


    Dear Stephen,

    Well said, but doing ‘at limited extent’ does not make someone an expert in the act. Certainly, additional information would influence critical reflections on future engagement with the process. For example, I am well informed about statistical methods based on my discipline specific context. But in the past 3 years, I have been using case study design, which embed statistical methods. Yet, I honestly feel I am not an expert until a critical mass eventuate from my efforts.

    Many thanks for the reference and inputs.

Viewing 9 posts - 1 through 9 (of 9 total)
  • You must be logged in to reply to this topic.