Discovering What Mattered: Answering Reverse Causal Questions by Detecting Unknown Treatment Assignment and Timing as Breaks in Panel Models

41 Pages Posted: 3 Feb 2022 Last revised: 3 Apr 2023

See all articles by Felix Pretis

Felix Pretis

University of Victoria, Department of Economics; University of Oxford - Institute for New Economic Thinking at the Oxford Martin School

Moritz Schwarz

Smith School of Enterprise and the Environment, University of Oxford; Climate Econometrics, Institute for New Economic Thinking at the Oxford Martin School

Date Written: January 31, 2022

Abstract

Much of empirical research focuses on forward causal questions (`Does X cause Y?') while reverse causal questions (`What causes Y?') can provide invaluable insights but is difficult to implement in practice. Here we operationalise the modelling of reverse causal questions through the detection of unknown treatment assignment and timing as structural breaks in fixed effects panel models. We show that conventional treatment evaluation of known interventions in a two-way fixed effects panel (often interpreted as difference-in-differences) is equivalent to allowing for heterogeneous structural breaks in the treated units' fixed effects. Using machine learning, we can thus detect previously unknown heterogeneous treatment effects as structural breaks in individual fixed effects corresponding to unit-specific treatment which can be subsequently attributed to potential causes (such as policy interventions). We demonstrate the feasibility of our approach by detecting the impact of ETA terrorism on Spanish regional GDP per capita without prior knowledge of its occurrence. Our proposed method to detect breaks in panel models can be readily implemented using our open-source R-package `gets' with the `getspanel' update or using the (adaptive) LASSO.

Keywords: Panel Data, Two-Way Fixed Effects, Treatment, Policy Evaluation, Difference-in-Differences; Break Detection, Indicator Saturation, Adaptive LASSO, Machine Learning

JEL Classification: C21, C23, C52

Suggested Citation

Pretis, Felix and Schwarz, Moritz, Discovering What Mattered: Answering Reverse Causal Questions by Detecting Unknown Treatment Assignment and Timing as Breaks in Panel Models (January 31, 2022). Available at SSRN: https://ssrn.com/abstract=4022745 or http://dx.doi.org/10.2139/ssrn.4022745

Felix Pretis (Contact Author)

University of Victoria, Department of Economics ( email )

3800 Finnerty Rd
Victoria, British Columbia V8P 5C2
Canada

University of Oxford - Institute for New Economic Thinking at the Oxford Martin School ( email )

Eagle House
Walton Well Road
Oxford, OX2 6ED
United Kingdom

Moritz Schwarz

Smith School of Enterprise and the Environment, University of Oxford ( email )

South Parks Road
Oxford, OX1 3QY
United Kingdom

HOME PAGE: http://www.moritzschwarz.org

Climate Econometrics, Institute for New Economic Thinking at the Oxford Martin School ( email )

Oxford
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
553
Abstract Views
1,859
Rank
94,292
PlumX Metrics