Search
Program Calendar
Browse By Day
Browse By Person
Browse By Room
Browse By Category
Browse By Session Type
Browse By Research Area
Search Tips
ASC Home
Personal Schedule
Sign In
X (Twitter)
Mediation analysis and structural equation modelling are both popular methodologies to describe and test complex criminological theories. This paper will demonstrate the importance of relying on the potential outcomes framework and applying causal mediation analysis with sensitivity analyses to test the robustness and potential causality in such settings. Four experiments were conducted, manipulating either perception of the procedural justice or the legality of the police or both. It will be shown here that approximately a third to half of the seemingly significant relationships were found to be spurious. Nevertheless, the analyses were also able to identify pertinent pathways and provide further evidence that procedural justice and legality are powerful predictors of legitimacy and that certain aspects of legitimacy (especially normative alignment with the police) do increase the willingness to cooperate with the police. The current framework will also allow for causal inference under some considerably restrictive assumptions. The advantages and limitations of the methodology will be discussed with a brief overview of design-based alternatives to improve the causal interpretation of the results.