Specification tests for the propensity score
From MaRDI portal
Abstract: This paper proposes new nonparametric diagnostic tools to assess the asymptotic validity of different treatment effects estimators that rely on the correct specification of the propensity score. We derive a particular restriction relating the propensity score distribution of treated and control groups, and develop specification tests based upon it. The resulting tests do not suffer from the "curse of dimensionality" when the vector of covariates is high-dimensional, are fully data-driven, do not require tuning parameters such as bandwidths, and are able to detect a broad class of local alternatives converging to the null at the parametric rate , with the sample size. We show that the use of an orthogonal projection on the tangent space of nuisance parameters facilitates the simulation of critical values by means of a multiplier bootstrap procedure, and can lead to power gains. The finite sample performance of the tests is examined by means of a Monte Carlo experiment and an empirical application. Open-source software is available for implementing the proposed tests.
Recommendations
- A specification test for the propensity score using its distribution conditional on participation
- Propensity score model specification for estimation of average treatment effects
- On the Role of the Propensity Score in Efficient Semiparametric Estimation of Average Treatment Effects
- Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score
- Practical propensity score matching: a reply to Smith and Todd
Cites work
- scientific article; zbMATH DE number 3169866 (Why is no real title available?)
- scientific article; zbMATH DE number 4698 (Why is no real title available?)
- scientific article; zbMATH DE number 3223275 (Why is no real title available?)
- A CONSISTENT DIAGNOSTIC TEST FOR REGRESSION MODELS USING PROJECTIONS
- A Consistent Conditional Moment Test of Functional Form
- A consistent test of functional form via nonparametric estimation techniques
- A general double robustness result for estimating average treatment effects
- A simple consistent bootstrap test for a parametric regression function
- A specification test for the propensity score using its distribution conditional on participation
- An updated review of goodness-of-fit tests for regression models
- Approximation Theorems of Mathematical Statistics
- Asymptotic Theory of Integrated Conditional Moment Tests
- Bootstrap Approximations in Model Checks for Regression
- Bootstrap and wild bootstrap for high dimensional linear models
- Characterizing Selection Bias Using Experimental Data
- Comparing nonparametric versus parametric regression fits
- Consistent Estimation of Models Defined by Conditional Moment Restrictions
- Consistent Model Specification Tests: Omitted Variables and Semiparametric Functional Forms
- Consistent model specification tests
- Dealing with limited overlap in estimation of average treatment effects
- Does matching overcome LaLonde's critique of nonexperimental estimators?
- Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score
- Efficient Semiparametric Estimation of Quantile Treatment Effects
- Empirical processes indexed by estimated functions
- Estimation and inference for distribution functions and quantile functions in treatment effect models
- Global power functions of goodness of fit tests.
- Goodness-of-Fit Tests for Linear and Nonlinear Time Series Models
- Inference on treatment effects after selection among high-dimensional controls
- Irregular identification, support conditions, and inverse weight estimation
- MODEL SELECTION AND INFERENCE: FACTS AND FICTION
- Matching As An Econometric Evaluation Estimator
- Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training Programme
- Matching on the estimated propensity score
- Model Checks for Generalized Linear Models
- Model-Based Direct Adjustment
- Non-parametric estimation of the residual distribution
- Nonparametric model checks for regression
- On the Role of the Propensity Score in Efficient Semiparametric Estimation of Average Treatment Effects
- On the lack of power of omnibus specification tests
- Probability for Statisticians
- Program evaluation and causal inference with high-dimensional data
- Specification analysis of linear quantile models
- Tailor-made tests for goodness of fit to semiparametric hypotheses
- Testing for Threshold Effects in Regression Models
- The central role of the propensity score in observational studies for causal effects
- The performance of estimators based on the propensity score
- The strong law under random censorship
- Weak convergence and empirical processes. With applications to statistics
Cited in
(9)- Propensity score model specification for estimation of average treatment effects
- Identification and estimation of triangular models with a binary treatment
- A specification test for the propensity score using its distribution conditional on participation
- Indirect inference with a non-smooth criterion function
- Testing independence between exogenous variables and unobserved errors
- pstest
- Testing for covariate balance using quantile regression and resampling methods
- Consistent tests for semiparametric conditional independence
- Difference-in-differences with multiple time periods
This page was built for publication: Specification tests for the propensity score
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q143736)
