Semiparametric Difference-in-Differences Estimators

By Alberto Abadie. 2005

2,284 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Gender Studies, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/e3f7a31e2b89afcfa3519180d7eec239b53db413

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 Gender Studies

In Statistics and Probability

Citations in the corpus

Difference-in-Differences with multiple time periods (2018, methodology): “Interestingly, in the standard DID setup of two periods only, E [p2 (X)C/ (1− p2 (X))] = E [G2], and the results of Theorem 1 reduce to Lemma 3.1 in Abadie (2005).”
On the Use of Two-Way Fixed Effects Regression Models for Causal Inference with Panel Data (2020, background): “(2018) proposed a weighted two-way fixed effects estimator as a bias adjustment to the synthetic control method of Abadie et al. (2010) in the settings where a single unit is treated only once at the last time period.”
Two-way Fixed Effects and Differences-in-Differences Estimators with Several Treatments (2020, positive): “It is a generalization of the standard common trends assumption in DID models (see, e.g., Abadie, 2005).”
Doubly robust difference-in-differences estimators (2018, positive): “Although one can use semi/non-parametric estimators for both the outcome regressions and the propensity score, see e.g. Heckman et al. (1997), Abadie (2005), Chen et al. (2008) and Rothe and Firpo (2018), in what follows we focus our attention on flexible parametric first step estimators.”
Difference-in-differences and matching on outcomes: a tale of two unobservables (2018, background): “The key assumption for the difference-in-differences is that after controlling for observable confounders, changes in expected non-treatment outcomes between periods t and t′ are mean independent of treatment assignment (Abadie 2005; Angrist and Pischke 2008; Lechner 2010; O’Neill et al.”
A Martingale Representation for Matching Estimators (2012, methodology): “The term RN is the conditional bias of matching estimator described in Abadie and Imbens (2006). This term is zero if all matches are perfect (that is, if all matching discrepancies, Xi − Xj for j ∈ JM(i), are zero), or if the regression μ0 is a constant function.”
Econometric Methods for Program Evaluation (2018, methodology): “However, because of space limitations, we omit Bayesian methods (see Rubin 1978, 2005) and finite-sample frequentist methods based on randomization (see Abadie et al. 2017a, Neyman 1923). Imbens & Rubin (2015) give an overview of many of these methods.”
Statistical Inference for Average Treatment Effects Estimated by Synthetic Control Methods (2019, methodology): “For example, the synthetic control method proposed by the seminal work of Abadie and Gardeazabal (2003), and Abadie, Diamond and Hainmeller (2010) can be used successfully to estimate average treatment effects (ATE).”
Efficient Estimation of Data Combination Models by the Method of Auxiliary-to-Study Tilting (AST) (2016, methodology): “If Assumption 2 happens to be true in the sampled populations, then AST will be more efficient than the propensity score reweighting approach of Abadie (2005).”
Fuzzy Differences-in-Differences (2015, methodology): “(2004) and Abadie (2005) consider a conditional version of the common trend assumption in sharp DID designs, and adjust for covariates using propensity score methods. Our Wald-DID estimator with covariates is related to their estimators. Bonhomme and Sauder (2011) consider a linear model allowing fo”
The Augmented Synthetic Control Method (2018, methodology): “SCM was introduced by Abadie and Gardeazabal (2003) and Abadie et al. (2010, 2015) and is the subject of an extensive methodological literature; see Abadie (2019) and Samartsidis et al.”
Who Takes You to the Dance? How Partners’ Institutional Logics Influence Innovation in Young Firms (2015, methodology): “The primary method was difference-in-differences analysis (Abadie, 2005; Smith and Todd, 2005; Short and Toffel, 2010).”
What’s trending in difference-in-differences? A synthesis of the recent econometrics literature (2022, positive): “Indeed, as shown by Abadie (2005), under Assumptions 2, 6 and 7, the ATT is identified using the following inverse probability weighting (IPW) formula: As in the regression adjustment approach, researchers can use the ‘‘plug-in principle’’ to estimate the ATT by plugging in an estimate of the…”
Quantile treatment effects in difference in differences models under dependence restrictions and with only two time periods (2017, methodology): “In the following corollary, we only consider the case with time invariant covariates, following the DID literature with repeated cross sections (Abadie, 2005; Melly and Santangelo, 2015).”
The Test-Optional Movement at America’s Selective Liberal Arts Colleges (2015, background): “…assumption that treated and control groups would exhibit parallel trends in the absence of intervention (Angrist & Pischke, 2009)—which, according to Abadie (2005), “may be implausible if pre-treatment characteristics that are thought to be associated with the dynamics of an outcome variable are…”
The Impact of Gurus: Parker Grades and en primeur Wine Prices* (2008, positive): “It is essentially the same as the identification restriction considered by Heckman et al. (1997), and Abadie (2005).12 Under restriction (2) and using that Pi(2003) = Pi0(2003), the ATET can be rewritten as (see Heckman et al. (1997), and Abadie (2005)) ATET = E[Pi1(2002)− Pi0(2003)|Di(2002) =…”