Synthetic instruments in DiD designs with unmeasured confounding

Unmeasured confounding and selection into treatment are key threats to reliable causal inference in Difference-in-Differences (DiD) designs. In practice, researchers often use instrumental variables to address endogeneity concerns, for example through shift-share instruments. However, in many settings instruments may be correlated with unobserved confounders, exhibiting pre-trends. In this paper we explore the use of synthetic controls to address unmeasured confounding in IV-DiD settings. We propose a synthetic IV estimator that partials out the unmeasured confounding and derive conditions under which it is consistent and asymptotically normal, when the standard two-stage least squares is not. Motivated by the finite sample properties of our estimator we then propose an ensemble estimator that might address different sources of bias simultaneously. We illustrate our method through a simulation exercise and two shift-share empirical applications: the Syrian refugee crisis effect on Turkish labor markets and the impact of Chinese imports on US manufacturing employment.

• Publication year

  2024

• Venue

  Social Science Research Network

• Publication date

  Unknown publication date

• Fields of study

  Not labeled

• Identifiers
  DOI 10.2139/ssrn.4716511
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The labor market effects of Venezuelan migration to Colombia: reconciling conflicting results

  2022cited by this paper
• Synthetic Controls in Action

  2022influential reference
• The Impact of Mass Migration of Syrians on the Turkish Labor Market

  2022cited by this paper
• Predictor Selection for Synthetic Controls

  2022cited by this paper
• Formal Effects of Informal Labor Supply: Evidence from the Syrian refugees in Turkey

  2022cited by this paper
• Benefits and costs of matching prior to a difference in differences analysis when parallel trends does not hold

  2022cited by this paper
• Causal Matrix Completion

  2021cited by this paper
• Revisiting event study designs: robust and efficient estimation

  2021cited by this paper
• Is It Merely a Labor Supply Shock? Impacts of Syrian Migrants on Local Economies in Turkey

  2021cited by this paper
• Non-random exposure to exogenous shocks: theory and applications

  2020cited by this paper
• Bartik Instruments: What, When, Why, and How

  2020cited by this paper
• Pre-test with Caution: Event-study Estimates After Testing for Parallel Trends

  2019cited by this paper
• On Policy Evaluation with Aggregate Time-Series Shocks

  2019cited by this paper
• Pre-Event Trends in the Panel Event-Study Design

  2019cited by this paper
• Shift-Share Designs: Theory and Inference*

  2018cited by this paper
• Factor models with many assets: Strong factors, weak factors, and the two-pass procedure

  2018cited by this paper
• NBER WORKING PAPER SERIES MATRIX COMPLETION METHODS FOR CAUSAL PANEL DATA MODELS

  2018cited by this paper
• Shift-Share Instruments and the Impact of Immigration

  2018cited by this paper
• The Augmented Synthetic Control Method

  2018cited by this paper
• Quasi-Experimental Shift-Share Research Designs.

  2018cited by this paper
• Synthetic Difference In Differences

  2018cited by this paper
• Proxy Controls and Panel Data.

  2018cited by this paper
• The Labor Market Effects of a Refugee Wave

  2018cited by this paper
• Debiasing and $t$-tests for synthetic control inference on average causal effects

  2018cited by this paper
• The Wage Impact of the Marielitos: A Reappraisal

  2017cited by this paper
• Synthetic controls with imperfect pretreatment fit

  2016cited by this paper
• Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder.

  2016cited by this paper
• Compulsory Education and the Benefits of Schooling

  2014cited by this paper
• Comparative Politics and the Synthetic Control Method

  2014cited by this paper
• A Martingale Representation for Matching Estimators

  2012cited by this paper
• Synthetic Control Methods for Comparative Case Studies: Estimating the Effect of California’s Tobacco Control Program

  2010cited by this paper
• Panel Data Models With Interactive Fixed Effects

  2009cited by this paper
• Sampling from large matrices: An approach through geometric functional analysis

  2005cited by this paper
• The Economic Costs of Conflict: A Case Study of the

  2003cited by this paper
• Protective or Counter-Productive? Labor Market Institutions and the Effect of Immigration on EU Natives

  2003cited by this paper
• Did Unilateral Divorce Laws Raise Divorce Rates? A Reconciliation and New Results

  2003cited by this paper
• Immigrant Inflows, Native Outflows, and the Local Labor Market Impacts of Higher Immigration

  2001cited by this paper
• The Impact of Mass Migration on the Israeli Labor Market

  2001cited by this paper
• The Impact of the 1962 Repatriates from Algeria on the French Labor Market

  1992cited by this paper
• The Impact of the Mariel Boatlift on the Miami Labor Market

  1990cited by this paper
• Martingale Limit Theory and Its Application

  1980cited by this paper
• Massachusetts Institute of Technology Department of Economics Working Paper Series the China Syndrome: Local Labor Market Effects of Import Competition in the United States the China Syndrome: Local Labor Market Effects of Import Competition in the United States *

  year unknowncited by this paper

• No citing papers are available for this paper.