Causal inference in regression: advice to authors

The 2021 Nobel prize in economics was awarded to David Card, Joshua Angrist, and Guido Imbens. Card, together with his PhD supervisor the late Alan Krueger, developed empirical methods for investigating how policy interventions affect labor markets. Angrist and Imbens developed methods for identifying causes from real-world complexity. Collectively, this work on causal inference has come to redefine how economists conduct research. A parallel storey for the emergence and growth of causal methods unfolded a quarter-century earlier in the discipline of epidemiology (Hill, 1965). Formal methods for causal inference trace an even longer history, beginning with the work of Sewall Wright on biological development and inheritance (Wright, 1921, 1923, 1934). Most empirical research published in Religion, Brain & Behavior is produced by scientists working in psychology, a field in which methods for causal inference remain poorly developed (see Rohrer, 2018). Here, we offer advice to RBB authors hoping to address causal inference using regression, ANOVA, and structural equation modeling.