“Analyzing Relations of Necessity in Survey Research: Incorporating Notions of Fuzzy-Set Qualitative Comparative Analysis and Bootstrap” by Daisuke Mori of Kumamoto University.
Correlation coefficients often used in quantitative research, such as survey research, cannot adequately measure certain key aspects within the relation of necessity. In this paper, I focus on Qualitative Comparative Analysis (QCA), enabling the analysis of set relations or relations of necessity and sufficiency, and try to incorporate it into the analysis of survey research. I present the parameters of fit in a fuzzy-set QCA to measure such a relation. I also show the methods used to conduct statistical inferences to understand the properties of a population based on a random sample from that population. For example, I analyzed the survey data on the purpose of tort damages in the case of a defective car accident in Japan. In this survey, respondents were asked about the extent to which they considered five factors in deciding the amount of damages: compensation for monetary loss, punishment, compensation for mental suffering, deterrence, and satisfying the feeling of retribution. I found that compensation for monetary loss is not correlated with punishment, deterrence, and satisfying the feeling of retribution. However, compensation for monetary loss is a necessary condition. The analysis of relations of necessity can highlight relations that have not been detected by conventional statistical analysis based on correlations.