An IV Model of Quantile Treatment Effects

By Victor Chernozhukov, Christian Hansen. 2002

1,113 citations recorded by the source corpus.

The ability of quantile regression models to characterize the heterogeneous impact of variables on different points of an outcome distribution makes them appealing in many economic applications. However, in observational studies, the variables of interest (e.g., education, prices) are often endogenous, making conventional quantile regression inconsistent and hence inappropriate for recovering the causal effects of these variables on the quantiles of economic outcomes. In order to address this problem, we develop a model of quantile treatment effects (QTE) in the presence of endogeneity and obtain conditions for identification of the QTE without functional form assumptions. The principal feature of the model is the imposition of conditions that restrict the evolution of ranks across treatment states. This feature allows us to overcome the endogeneity problem and recover the true QTE through the use of instrumental variables. The proposed model can also be equivalently viewed as a structural simultaneous equation model with nonadditive errors, where QTE can be interpreted as the structural quantile effects (SQE). Copyright The Econometric Society 2005.

Subfields: Economics and Econometrics, Statistics and Probability

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

The Econometrics of Randomized Experiments (2016, background): “(4.9) Such quantile treatment effects have been studied in Doksum (1974) and Lehman (1974), and more recently in Abadie, Angrist and Imbens (2002), Chernozhukov and Hansen (2005), Firpo (2007), Bitler, Gelbach and Hoynes (2002).”
Do remittances improve income inequality? An instrumental variable quantile analysis of the Kenyan case (2016, methodology): “To achieve this, we use the instrumental variable quantile approach suggested by Chernozhukov and Hansen (2005, 2008) and implemented for the analysis of inequality and wage dispersion by Harding and Lamarche (2009).”
Econometric Evaluation of Social Programs, Part I: Causal Models, Structural Models and Econometric Policy Evaluation (2007, methodology): “They may instead consist of distributions of Y(j, ω) and Y(k, ω) separately [Abadie, Angrist and Imbens (2002), Chernozhukov and Hansen (2005)].”
Partial Identification in Triangular Systems of Equations With Binary Dependent Variables (2011, methodology): “Similarly, we cannot follow the quantile instrumental variable-approach used in Chernozhukov and Hansen (2005) and Chernozhukov et al. (2007), which would require g 1 to be strictly increasing in 1 .”
Estimation of nonparametric conditional moment models with possibly nonsmooth moments (2008, methodology): “See Chernozhukov and Hansen (2005) and Chernozhukov, Imbens and Newey (hereafter CIN, 2007) for identification;4 CIN (2007) for consistency, and Horowitz and Lee (hereafter HL, 2007) for consistency and convergence rate of their respective estimators of the NPQIV model (1.3).”
Smoothing Quantile Regressions (2019, positive): “Third, one could exploit the connection between QR and quantile instrumental variable models (Kaido and Wuthrich 2018) to obtain smoother estimators and better inferential procedures (Chernozhukov and Hansen 2005; Jun 2008; Andrews and Mikusheva 2016; de Castro et al. 2019).”
Control functions in nonseparable simultaneous equations models (2014, methodology): “2 Identification of various features of this triangular model has been widely studied under different sets of assumptions, including Newey, Powell, and Vella (1999), Chesher (2003), Florens et al. (2008), Imbens and Newey (2009), Torgovitsky (2012), and D’Haultfuille and Fevrier (2012), among others”
Instrumental variable estimation of nonseparable models (2007, methodology): “This is a local version of the global identification condition of Chernozhukov and Hansen (2005) for this example.”
Nonparametric Instrumental Variables Estimation of a Quantile Regression Model (2006, background): “Chernozhukov and Hansen (2005b) give conditions under which g in (1.1)-(1.2) is identified.”
On the Testability of Identification in Some Nonparametric Models With Endogeneity (2012, methodology): “For instance, Theorem 3.2 does not apply whenXi has discrete support under νx—a setting prominently studied in Chernozhukov and Hansen (2005).”
Econometric Methods for Program Evaluation (2018, background): “Chernozhukov and Hansen (2005, 2013) propose a rank similarity condition under which they derive an estimator of quantile treatment effects for the entire population (rather than for compliers only).”