Tool for researchers:
NCA is an approach and tool for researchers who wish to build or test theory with empirical data and write impactful publications.
Benefits for researchers:
NCA can be used by any researcher in the social sciences who wants:
- To contribute to an academic field and to demonstrate to its academic community (including journal editors and reviewers) that the research provides new insights with academic rigor and practical relevance.
- To gain new substantive insights by expressing social science phenomena in terms of necessity; using NCA provides an alternative perspective, may enhance existing research, or falsify theories;
- To apply a straightforward and rigorous method that does not have the complexities of current regression based methods (e.g., endogeneity, multicollinearity) because the necessary condition operates in isolation from other variables (i.e., it is always present in the successful outcome)
- To give a clear practical meaning to the results, because identified necessary condition must always be put and kept in place in practice;
Complements researchers’ current methods:
Researchers can use NCA as a separate technique, or in combination with existing techniques. Researchers who use regression-bases analyses (e.g., multiple regression, structural equation modelling, partial least squares) can complement their analyses with NCA, to better explain the (lack of) outcome of interest. Researchers who use configurational analyses (e.g., fsQCA) can complement their analyses with NCA, to identify necessary conditions with more detail. NCA can be used for any research design. Case study researchers can use NCA for identifying a necessary condition as a common characteristic of successful cases (cases where the outcome is present or high). Researchers who use experiments can consider to complement a sufficiency experiment (adding a condition in cases without the outcome and checking whether the outcome increases) with a necessity experiment (removing a condition in cases with the outcome, and checking whether the outcome decreases). Approaches for sampling and measurement are not different for NCA than for data analysis methods.