Configurational reasoning and the importance of internal fit among conceptually distinct characteristics are pervasive ideas in organizational research. However, for a long time, the field lacked adequate quantitative methods to test configurational theory. The introduction of Qualitative Comparative Analysis (QCA) renewed researchers’ interest in the analysis of ideal types and causal complexity, but the method’s foundations in set theory and Boolean algebra complicate its use, especially in larger sample sizes. This article introduces Configuration Distance Analysis (CDA), a probabilistic technique to find and test for ideal types. It combines configurational reasoning with principles and methods from spatial econometrics. A reanalysis of five datasets demonstrates CDA’s key advantages over QCA. Furthermore, the method’s performance and robustness are tested in Monte Carlo simulations, the results of which indicate that the method performs best in in medium-N and large-N samples. The talk concludes with recommendations for researchers, method extensions, and limitations of CDA.
Torsten Biemann has been Professor of Human Resources Management and Leadership at the University of Mannheim since 2013. He is the author of numerous national and international publications focusing on human resources strategy, career, leadership and diversity. In addition, he is a member of the editorial advisory board of various human resources journals. He represents the approach of an evidence-based personnel management in order to bridge the gap between theory and practice in the personnel area. According to Personalmagazin, he is one of the 40 leading minds in human resources.
More info about Prof. Biemann