Understanding the Past: Statistical Analysis of Causal Attribution

Abstract

Would the third-wave democracies have been democratized without prior modernization? What proportion of the past militarized disputes between non-democracies would have been prevented had those dyads been democratic? Although political scientists often ask these questions of causal attribution, existing quantitative methods fail to address them. This paper proposes an alternative statistical methodology based on the widely accepted counterfactual framework of causal inference. The contribution of this paper is threefold. First, the paper clarifies differences between causal attribution and causal effects by specifying the type of research questions to which each quantity is relevant. Second, it provides a clear resolution of the long-standing methodological debate on "selection on the dependent variable." Third, the paper derives new nonparametric identification results, showing that the complier probability of causal attribution can be identified using an instrumental variable. The proposed framework is illustrated via empirical examples from three subfields of political science.

Declaring and Diagnosing Research Designs

“…In fact, experiments are in general not able to solve the identification problem for causeof-effects questions (Dawid 2000) and this may be one poor reason for why these questions are often ignored by quantitative researchers. Exceptions include Yamamoto (2012) and Balke and Pearl (1994).…”

Why ask Why? Forward Causal Inference and Reverse Causal Questions

“…Before going on, let us clarify that we are using the terms "forward" and "reverse" to refer not to time but to the sequence of the statistical model. As Fearon (1991) and Yamamoto (2012) discuss, counterfactual reasoning can also be applied to assess attributions of causes of past events. We label this historical reasoning as "forward causal inference" as well, as it is based on the estimation of effects of defined treatments.…”

Statistics in Court

“…However, in deciding the case, the judge is interested in a subtly different question: whether the worker's exposure to the chemical in this factory caused this particular cancer. The statistician's question is one of casual effect, while the judge's is one of causal attribution 4 …”