Develops novel bounds on average treatment effects by pooling limited information across observations for robustness under unconfoundedness, with inference methods.
A simple, short, but never-empty confidence interval for partially identified parameters
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
econ.EM 3verdicts
UNVERDICTED 3representative citing papers
Dynamic random coefficient panel models with predetermined regressors are partially identified in short panels, with characterized identified sets for the mean, variance, and CDF of the coefficient distribution enabling tractable estimation.
Develops sharp partial identification bounds and semiparametrically efficient inference for complier treatment effects in nonparametric sample selection models with endogenous treatment.
citing papers explorer
-
Bounding Treatment Effects by Pooling Limited Information across Observations
Develops novel bounds on average treatment effects by pooling limited information across observations for robustness under unconfoundedness, with inference methods.
-
Identification and estimation of dynamic random coefficient models
Dynamic random coefficient panel models with predetermined regressors are partially identified in short panels, with characterized identified sets for the mean, variance, and CDF of the coefficient distribution enabling tractable estimation.
-
Sharp Bounds and Inference in Sample Selection Models with Treatment Endogeneity
Develops sharp partial identification bounds and semiparametrically efficient inference for complier treatment effects in nonparametric sample selection models with endogenous treatment.