LAUSR

Abstract Claiming that high levels of an independent variable represent a necessary-but-not-sufficient condition for an outcome suggests that the outcome is only possible – but not guaranteed – with high levels of that variable. Necessary condition analysis (NCA) allows researchers to determine if an observed relation between an independent variable and a dependent variable is consistent with such a necessary-but-not-sufficient relation. Using both archival and primary data, we apply Dul's (2016) necessary condition analysis techniques to common correlates of academic success in college. We find data patterns that are consistent with necessary-but-not-sufficient conditions for academic success for a variety of variables including class attendance, grit-perseverance, growth mindset, prior achievement, and admissions test scores. Our findings imply that some individual characteristics and behaviors may constrain the level of grades possible in college and that researchers may benefit from considering necessity models of academic performance. We discuss further applications of necessary condition analysis in educational research as a supplement to traditional data analysis.