Co-authored with Jordi Muñoz and Albert Falcó-Gimeno
Download the paper here
An increasing number of studies exploit the occurrence of unexpected events during the fieldwork of public opinion surveys to estimate causal effects. In this paper we present this identification strategy based on unforeseen and salient events that split the sample of public opinion surveys into treatment and control groups: the Unexpected Event during Surveys Design (UESD). In particular we focus on the assumptions under which unexpected events can be exploited to estimate causal effects (mainly, ignorability and excludability), and discuss the potential threats to identification, paying especial attention to the observable and testable implications of these assumptions. We present various estimation strategies as well as a series of robustness checks that can be used to lend credibility to the causal estimates. We illustrate the discussion of this method with an original study of the impact of the Charlie Hebdo terrorist attacks (Paris, 01/07/2015) on individuals’ satisfaction with government using data of the European Social Survey, which highlights the strengths and weaknesses of the UESD.