“QCA exists in a nether region between qualitative and quantitative research”

‘Highlighting QCA’s reliance on two-element Boolean algebra and propositional logic brings the weaknesses of QCA into sharp relief. The distinction between QCA and conventional statistics is not a difference between “set-theoretic” methods and what QCA researchers call “non-set-theoretic” methods (Schneider and Wagemann 2012) […]. Conventional statistics are set-theoretic methods. […] What truly sets QCA apart from conventional statistics is the former’s embrace of the limitations of two-element Boolean algebra and propositional logic. QCA exists in a nether region between qualitative and quantitative research; it exhibits neither the depth of small-n qualitative research nor the power of quantitative research.’ (Clarke 2020, p. 553)

Clarke, K. A. (2020). Logical Constraints: The Limitations of QCA in Social Science Research. Political Analysis, 28(4), 552–568.

QCA versus regression trees

I have been pondering the relationship between qualitative comparative analysis (QCA) and regression trees – and obviously I’m not the first to do so. Here’s an interesting blog post by Rick Davies (2012), which includes a reanalysis of a QCA using a decision tree.

There’s also a 2014 EES talk: