<p>Observational studies often present challenges for causal inference due to confounding, treatment heterogeneity, and limited overlap in covariate distributions. In this paper, we illustrate how modern causal inference methods can be applied to large-scale academic salary data to address these issues in practice. Using records from 12,039 tenure-track faculty in the University of North Carolina system, we link administrative salary data with bibliometric indicators of research productivity and institutional classifications. To estimate the causal effect of gender on faculty compensation, we combine propensity score matching with nonparametric methods based on causal forests, which flexibly account for discipline, academic rank, years of experience, and productivity measures. Results indicate that female faculty earn approximately six percent less than comparable male colleagues, with substantial variation in the gap across career stages and levels of research output. Taken together, these findings provide quantitative evidence of structural pay disparities and highlight the value of causal inference approaches for uncovering inequities in complex social systems such as higher education.</p>