Combining counterfactual outcomes and ARIMA models for policy evaluation

Abstract

The Rubin Causal Model (RCM) is a framework that allows to define the causal effect of an intervention as a contrast of potential outcomes. In recent years, several methods have been developed under the RCM to estimate causal effects in time series settings. None of these makes use of ARIMA models, which are instead very common in the econometrics literature. In this paper, we propose a novel approach, named Causal-ARIMA (C-ARIMA), to define and estimate the causal effect of an intervention in observational time series settings under the RCM. We first formalize the assumptions enabling the definition, the estimation and the attribution of the effect to the intervention. We then check the validity of the proposed method with a simulation study. In the empirical application, we use C-ARIMA to assess the causal effect of a permanent price reduction on supermarket sales. The CausalArima R package provides an implementation of the proposed approach.

How does technology‐based monitoring affect street‐level bureaucrats' behavior? An analysis of body‐worn cameras and police actions

“…It exploits the full series of data to establish the historical pattern and uses it to estimate the time‐varying treatment effect. Meanwhile, non‐equivalent dependent variables can be easily combined with pre‐treatment series to formulate a synthetic control and mitigate inferential biases when non‐treated units are absent (Menchetti et al., 2023). In the present study, non‐treated units would be police agencies that satisfy two criteria: 1) the agency did not obtain body‐worn cameras during the analyzed time frame; and 2) the agency provides time‐series data for all the dependent variables: number of stops, frisks, searches, citations, arrests, race of suspects, whether frisk/search uncovered drugs or weapons, and whether a stop happened during a calls‐for‐service dispatch.…”

Quantitative Evaluation of Domestic Cultural and Tourism Integration Policies Based on PMC Index Modeling

“…Literature [13] conducted text mining and policy consistency modeling in fire safety education policies and used the PMC index model to evaluate policies in this field, pointing out the actual strengths and weaknesses of current policies. Literature [14] proposed a new observational model, cas-ARIMA, for policy assessment in the field of economics, which effectively extracted the causal effects of economic policy interventions. Literature [15] analyses the impact of European agricultural policies on farmers' incomes, based on the discussion of farmers' income risk, and proposes a new view of agricultural policy optimization based on the modeling of farmers' household incomes and policy measures.…”