Regional Policy Evaluation: Interactive Fixed Effects and Synthetic Controls

By L. Gobillon, T. Magnac. Review of Economics and Statistics, 2016

392 citations recorded by the source corpus.

Abstract In this paper, we investigate the use of interactive effect or linear factor models in regional policy evaluation. We contrast treatment effect estimates obtained using Bai (2009) with those obtained using difference in differences and synthetic controls (Abadie and coauthors). We show that difference in differences are generically biased, and we derive support conditions for synthetic controls. We construct Monte Carlo experiments to compare these estimation methods in small samples. As an empirical illustration, we provide an evaluation of the impact on local unemployment of an enterprise zone policy implemented in France in the 1990s.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/fbf99e5562a0780856e7c4ed615ab2ab66c0dff3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Matrix Completion, Counterfactuals, and Factor Analysis of Missing Data (2019, background): “Gobillon and Magnac (2016) showed that if the true model is a linear factor model, synthetic controls are equivalent to factor models if the factor loadings and exogenous covariates for the treated are in the support of these variables for the control group.”
Synthetic Control and Inference (2017, methodology): “In addition to these two methods, we can also entertain the possibility that if both T0 and J are large, it may be possible to use the panel technique as in Bai (2009) as well.13 See, e.g., Gobillon and Magnac (2016).”
Synthetic Control Method: Inference, Sensitivity Analysis and Confidence Sets (2018, background): “…crime (Pinotti (2012b), Pinotti (2012a), Saunders et al. (2014)), social connections (Acemoglu et al. (2013)), and local development (Ando (2015), Gobillon & Magnac (2016), Kirkpatrick & Bennear (2014), Liu (2015), Possebom (2017) and Severnini (2014)). of the parameter that affects the decision…”
Synthetic controls with imperfect pretreatment fit (2016, methodology): “Remark 5 Our main result that the original and the demeaned SC estimators are generally asymptotically biased if there are unobserved time-varying confounders (Propositions 1 and 2) still applies if we also relax the non-negative and the adding-up constraints, which essentially leads to the panel da”
A Practical Guide to Counterfactual Estimators for Causal Inference with Time-Series Cross-Sectional Data (2020, methodology): “They include (1) the fixed-effect counterfactual (FEct) estimator, of which difference-in-differences (DiD) is a special case, (2) the interactive fixed-effect counterfactual (IFEct) estimator (Gobillon and Magnac 2016; 1The second assumption is implied by strict exogeneity.”
Synthetic Difference In Differences (2018, neutral): “We also note recent papers that draw from these ideas in connection to SC type analyses, including Chan and Kwok ( 2020 ) and Gobillon and Magnac ( 2016 ) .”