Optimal Inference in a Class of Regression Models
From MaRDI portal
Abstract: We consider the problem of constructing confidence intervals (CIs) for a linear functional of a regression function, such as its value at a point, the regression discontinuity parameter, or a regression coefficient in a linear or partly linear regression. Our main assumption is that the regression function is known to lie in a convex function class, which covers most smoothness and/or shape assumptions used in econometrics. We derive finite-sample optimal CIs and sharp efficiency bounds under normal errors with known variance. We show that these results translate to uniform (over the function class) asymptotic results when the error distribution is not known. When the function class is centrosymmetric, these efficiency bounds imply that minimax CIs are close to efficient at smooth regression functions. This implies, in particular, that it is impossible to form CIs that are tighter using data-dependent tuning parameters, and maintain coverage over the whole function class. We specialize our results to inference on the regression discontinuity parameter, and illustrate them in simulations and an empirical application.
Recommendations
- Optimal Inference in Regression Models with Nearly Integrated Regressors
- scientific article; zbMATH DE number 4068057
- Optimal estimation in random coefficient regression models
- Statistical inference for the optimal approximating model
- Optimal estimation in additive regression models
- On statistical estimation and inferences in optional regression models
- Optimal estimation methods under weakened linear restrictions in regression
Cited in
(32)- Minimax linear estimation at a boundary point
- Augmented minimax linear estimation
- Optimizing the tie-breaker regression discontinuity design
- Testing continuity of a density via g-order statistics in the regression discontinuity design
- Impossible inference in econometrics: theory and applications
- Inference of local regression in the presence of nuisance parameters
- Regression discontinuity designs, white noise models, and minimax
- Optimal estimation methods under weakened linear restrictions in regression
- Why randomize? Minimax optimality under permutation invariance
- On nonparametric inference in the regression discontinuity design
- scientific article; zbMATH DE number 954504 (Why is no real title available?)
- Smoothness-Adaptive Contextual Bandits
- Confidence Intervals for Nonparametric Empirical Bayes Analysis
- Rejoinder: Confidence Intervals for Nonparametric Empirical Bayes Analysis
- What's trending in difference-in-differences? A synthesis of the recent econometrics literature
- Permutation Tests at Nonparametric Rates
- Robust empirical Bayes confidence intervals
- Nonlinear and nonseparable structural functions in regression discontinuity designs with a continuous treatment
- Combining observational and experimental datasets using shrinkage estimators
- A Correction for Regression Discontinuity Designs With Group-Specific Mismeasurement of the Running Variable
- Debiased Inference of Average Partial Effects in Single-Index Models: Comment on Wooldridge and Zhu
- Asymptotically Uniform Tests After Consistent Model Selection in the Linear Regression Model
- Optimal HAR inference
- A more credible approach to parallel trends
- On uniform confidence intervals for the tail index and the extreme quantile
- Shrinkage methods for treatment choice
- Nonparametric regression under cluster sampling
- Noise-induced randomization in regression discontinuity designs
- Bias-aware inference in fuzzy regression discontinuity designs
- Empirical Bayes when estimation precision predicts parameters
- Flexible covariate adjustments in regression discontinuity designs
- Optimal method in multiple regression with structural changes
This page was built for publication: Optimal Inference in a Class of Regression Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4628444)
