Estimating derivatives of function-valued parameters in a class of moment condition models

DOI10.1016/J.JECONOM.2019.11.004MaRDI QIDQ2190207zbMATH OpenOpenAlexWikidataFDO

Authors Christoph Rothe, Dominik Wied

Publication date 18 June 2020

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1610.09363

zbMATH Keywords

quantile regressionconditional density estimationlocal linear smoothingdistribution regressionquantile partial effects

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Applications of statistics to economics (62P20) Auctions, bargaining, bidding and selling, and other market models (91B26)

Abstract: We develop a general approach to estimating the derivative of a function-valued parameter $het{a}_o(u)$ that is identified for every value of $u$ as the solution to a moment condition. This setup in particular covers many interesting models for conditional distributions, such as quantile regression or distribution regression. Exploiting that $het{a}_o(u)$ solves a moment condition, we obtain an explicit expression for its derivative from the Implicit Function Theorem, and estimate the components of this expression by suitable sample analogues, which requires the use of (local linear) smoothing. Our estimator can then be used for a variety of purposes, including the estimation of conditional density functions, quantile partial effects, and structural auction models in economics.

Recommendations

• Nonparametric instrumental variable derivative estimation
• Kernel methods for estimating derivatives of conditional quantiles
• Global nonparametric estimation of conditional quantile functions and their derivatives
• Estimation of possibly misspecified semiparametric conditional moment restriction models with different conditioning variables
• Design-adaptive nonparametric estimation of conditional quantile derivatives

Cites work

• scientific article; zbMATH DE number 991833 (Why is no real title available?)
• Censored regression quantiles
• Estimation of conditional quantile density function
• Extremum estimation and numerical derivatives
• Global nonparametric estimation of conditional quantile functions and their derivatives
• Inference on counterfactual distributions
• Kernel methods for estimating derivatives of conditional quantiles
• MULTIVARIATE LOCAL POLYNOMIAL REGRESSION FOR TIME SERIES:UNIFORM STRONG CONSISTENCY AND RATES
• Misspecification Testing in a Class of Conditional Distributional Models
• Nonparametric Identification of Risk Aversion in First-Price Auctions Under Exclusion Restrictions
• Nonparametric Statistical Data Modeling
• Optimal Nonparametric Estimation of First-price Auctions
• Partial distributional policy effects
• Quantile regression.
• Quantile-based nonparametric inference for first-price auctions
• Regression Quantiles
• Uniform bias study and Bahadur representation for local polynomial estimators of the conditional quantile function

Cited in

(3)

• Parameter Estimation for the Bateman Function via Moments of the Empirical Curve
• Truncating the exponential with a uniform distribution
• Partial derivative estimation for underlying functional-valued process in a unified framework

This page was built for publication: Estimating derivatives of function-valued parameters in a class of moment condition models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2190207)