Generic Inference on Quantile and Quantile Effect Functions for Discrete Outcomes

DOI10.1080/01621459.2019.1611581MaRDI QIDQ3304840zbMATH OpenOpenAlexWikidataFDO

Authors Victor Chernozhukov, Iván Fernández-Val, Blaise Melly, Kaspar Wüthrich

Publication date 3 August 2020

Published in Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1608.05142, https://boris.unibe.ch/145832/

zbMATH Keywords

counterfactual distributiondecomposition analysisdistribution regressionquantile treatment effectuniform inference

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric hypothesis testing (62G10)

Abstract: Quantile and quantile effect functions are important tools for descriptive and causal analyses due to their natural and intuitive interpretation. Existing inference methods for these functions do not apply to discrete random variables. This paper offers a simple, practical construction of simultaneous confidence bands for quantile and quantile effect functions of possibly discrete random variables. It is based on a natural transformation of simultaneous confidence bands for distribution functions, which are readily available for many problems. The construction is generic and does not depend on the nature of the underlying problem. It works in conjunction with parametric, semiparametric, and nonparametric modeling methods for observed and counterfactual distributions, and does not depend on the sampling scheme. We apply our method to characterize the distributional impact of insurance coverage on health care utilization and obtain the distributional decomposition of the racial test score gap. We find that universal insurance coverage increases the number of doctor visits across the entire distribution, and that the racial test score gap is small at early ages but grows with age due to socio economic factors affecting child development especially at the top of the distribution. These are new, interesting empirical findings that complement previous analyses that focused on mean effects only. In both applications, the outcomes of interest are discrete rendering existing inference methods invalid for obtaining uniform confidence bands for observed and counterfactual quantile functions and for their difference -- the quantile effects functions.

Recommendations

• Estimation and inference for distribution functions and quantile functions in treatment effect models
• Estimation and inference for distribution and quantile functions in endogenous treatment effect models
• Instrumental quantile regression inference for structural and treatment effect models
• Finite sample inference for quantile regression models
• A direct approach to inference in nonparametric and semiparametric quantile models

Cites work

• A comparison between bootstrap methods and generalized estimating equations for correlated outcomes in generalized linear models
• Asymptotic properties of sample quantiles of discrete distributions
• Conditional quantile processes based on series or many regressors
• Confidence Intervals for Medians and Other Position Measures
• Confidence Limits for an Unknown Distribution Function
• Discrete quantile estimation
• Empirical probability plots and statistical inference for nonlinear models in the two-sample case
• Estimation and inference for distribution functions and quantile functions in treatment effect models
• Exchangeably weighted bootstraps of the general empirical process
• scientific article; zbMATH DE number 3551712 (Why is no real title available?)
• scientific article; zbMATH DE number 3637090 (Why is no real title available?)
• scientific article; zbMATH DE number 3008134 (Why is no real title available?)
• scientific article; zbMATH DE number 854575 (Why is no real title available?)
• Inference on counterfactual distributions
• Inference on the Quantile Regression Process
• Misspecification Testing in a Class of Conditional Distributional Models
• Non-Parametric Estimation. I. Validation of Order Statistics
• Nonparametric estimation and inference on conditional quantile processes
• Program evaluation and causal inference with high-dimensional data
• Quantile estimation with a complex survey design
• Quantile Regression under Misspecification, with an Application to the U.S. Wage Structure
• Quantile regression.
• Quantile treatment effects in the regression discontinuity design
• Quantiles for Counts
• Recursive confidence band construction for an unknown distribution function
• Regression Quantiles
• Regression rank scores and regression quantiles
• The cluster bootstrap consistency in generalized estimating equations
• Weak convergence and empirical processes. With applications to statistics

Cited in

(11)

• Quantile regression via the EM algorithm for joint modeling of mixed discrete and continuous data based on Gaussian copula
• Distributional (Single) Index Models
• Nonparametric identification and estimation of heterogeneous causal effects under conditional independence
• Network and panel quantile effects via distribution regression
• Regression adjustment for estimating distributional treatment effects in randomized controlled trials
• Distribution regression with censored selection
• Difference-in-Differences Estimator of Quantile Treatment Effect on the Treated
• The impact of public school choice: evidence from Los Angeles's zones of choice
• Mid-quantile regression for discrete panel data
• Stability and statistical inference for semidiscrete optimal transport maps
• Multivariate distribution regression

Describes a project that uses

Uses Software

• R

This page was built for publication: Generic Inference on Quantile and Quantile Effect Functions for Discrete Outcomes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3304840)