The Causal Implications of Mechanistic Thinking: Identification Using Directed Acyclic Graphs (DAGs)

Abstract

In analyzing causal claims, the most common evidentiary strategy is to use an experimental or quasi-experimental framework; holding all else constant, a treatment is varied and its effect on the outcome is determined. However, a second, quite distinct strategy is gaining prominence within the social sciences. Rather than mimic an experiment, researchers can identify causal relations by finding evidence for mechanisms that link cause and effect. In this chapter, we use Directed Acyclic Graphs (DAGs) to illustrate the power of using mechanisms. We show how mechanisms can aid in causal analysis by bringing additional variation to bear in instances where causal effects would otherwise not be identified. Specifically, we examine five generic situations where a focus on mechanisms using DAGs allows an analyst to warrant causal claims.