Irregular Identification, Support Conditions, and Inverse Weight Estimation

By Shakeeb Khan, Elie Tamer. 2010

297 citations recorded by the source corpus.

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

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning (2019, background): “It is necessary so to ensure that ρ πe is a function of pπb(J ), that is, is identifiable from the data (Khan and Tamer 2010).”
Semiparametric Estimation and Inference Using Doubly Robust Moment Conditions (2013, background): “For the latter, arguments analogous to those in Linton (1995), Ichimura and Linton (2005) or Cattaneo et al.”
Difference-in-Differences with multiple time periods (2018, background): “, Sherman and Le Cessie (2007), Kline and Santos (2012), Cheng et al.”
Double Debiased Machine Learning Nonparametric Inference with Continuous Treatments (2019, background): “(2019) and Oprescu et al. (2019) extend to more general functional forms.”
The Value of Knowing the Propensity Score for Estimating Average Treatment Effects (2016, background): “As pointed out for example by Linton (1995) or Robins and Ritov (1997), asymptotic approximations based on such conditions can be fragile in practice, especially in settings with many covariates.”
New Evidence on the Finite Sample Properties of Propensity Score Matching and Reweighting Estimators (2009, background): “Frölich (2004) focuses on the effect of treatment on the treated, or TOT = E[Yi(1)−Yi(0)|Ti = 1] = E[µ1(Xi)−µ0(Xi)|Ti = 1], and we maintain that focus here.”
Estimating Conditional Average Treatment Effects (2014, background): “Based on results, both theoretical (Khan and Tamer 2010) and experimental (Huber et al. 2012; Donald, Hsu, and Lieli 2014a), we expect the asymptotic distributions given in Theorems 1 and 2 to be worse small sample approximations in this case.”
Robust Inference Using Inverse Probability Weighting (2018, background): “Khan and Tamer (2010) show that, depending on tail behaviors of the probability weights, the variance bound of the IPW estimator can be infinite, which leads to a slower-than√ n convergence rate.”
Complementarity and Aggregate Implications of Assortative Matching: A Nonparametric Analysis (2014, unknown): “Stock (1989) studied policies that induce new input distributions.”
Asymptotic inference of causal effects with observational studies trimmed by the estimated propensity scores (2018, background): “Consequently, extreme estimated propensity scores induce large weights, which can result in a large variance and poor finite-sample properties (Kang & Schafer, 2007; Khan & Tamer, 2010).”
The Finite Sample Performance of Inference Methods for Propensity Score Matching and Weighting Estimators (2018, methodology): “Second, we investigate two simulation designs previously considered in Busso, DiNardo, and McCrary (2014), which are based on U.S. data from the National Supported Work (NSW), see LaLonde (1986), as well as the Panel Study of Income Dynamics (PSID), and vary them w.r.t. treatment selection.”
Econometric Analysis of Games with Multiple Equilibria (2012, background): “…conditions for Tamer’s result satisfied, this identification-at-infinity strategy will have important consequences for inference, as pointed out by Khan & Tamer (2010), leading to asymptotic convergence rates that are slower than parametric rates as the sample size (i.e., number of games)…”
Sieve Wald and QLR Inferences on Semi/Nonparametric Conditional Moment Models (2014, unknown): “Following Kahn and Tamer (2010) and Graham and Powell (2012) we call such a θ0 irregular.”
A Simple Estimator for Binary Choice Models with Endogenous Regressors (2015, methodology): “in Khan and Tamer (2010), and Khan and Nekipelov (2010a, 2010b).”
Overlap in observational studies with high-dimensional covariates (2017, background): “If it does not, there exists a parametric submodel for which this lower bound diverges, so no uniform guarantees of n1/2-consistency are possible (Khan & Tamer, 2010).”
A quantile correlated random coefficients panel data model (2016, unknown): “= C ( β (τ ; X) , β (τ ′; X) ∣∣X ∈ XM) Pr (X ∈ XM) + Υ1(τ, τ ′) +KΣδ(τ, τ ′)KM ′ (36)”