Indicator-driven data calibration of expert interviews in a configurational study

Abstract

Expert interviews can provide interesting data for the use in qualitative comparative analysis (QCA) to investigate complex social phenomena. To guide the challenging task of data calibration from qualitative data sets, techniques have already been suggested for the transformation of qualitative data into fuzzy sets. The current article follows existing guidelines and extends them with a system for indicator-based data calibration of expert interviews. While the underlying data set is confidential due to its corporate setting, in this article the analysis of the data is made transparent and hence reproducible for potential follow-up studies. First, the process of data collection is described, and the final data sample is characterized. Consequently, a system for indicator-based data calibration is presented and the calibration results for the empirical sample are provided in form of the set membership of cases and truth tables.

• Data collection from expert interviews is described for a configurational setting

• A combined indicator-based system is used for the calibration of qualitative data