How Far Are Automatically Chosen Regression Smoothing Parameters From Their Optimum?
We address the problem of smoothing parameter selection for nonparametric curve estimators in the specific context of kernel regression estimation. Call the ``optimal bandwidth the minimizer of the average squared error. We consider several automatically selected bandwidths that approximate the optimum. How far are the automatically selected bandwidths from the optimum? The answer is studied theoretically and through simulations. The theoretical results include a central limit theorem that quantifies the convergence rate and gives the differences asymptotic distribution. The convergence rate turns out to be excruciatingly slow. This is not too disappointing, because this rate is of the same order as the convergence rate of the difference between the minimizers of the average squared error and the mean average squared error.
- New approaches to model-free dimension reduction for bivariate regression
- Using bimodal kernel for inference in nonparametric regression with correlated errors
- Bandwidth selection for kernel estimate with correlated noise
- Optimal bandwidth choice for density-weighted averages
- On the consistency of the global minimizer of Mallow's criterion for nonparametric regression
- Lower bounds for bandwidth selection in density estimation
- Smoothed cross-validation
- Asymptotic comparison factors for smoothing parameter choices in regression problems
- Recursive estimation of intensity function of a Poisson random field
- On the estimation of prediction errors in linear regression models
- A short note on optimal bandwidth selection for kernel estimators
- Consistent bandwidth selection for kernel binary regression
- On residual sums of squares in non-parametric autoregression
- Nonparametric estimation of a regression function with dependent observations
- Asymptotic distribution of bandwidth selectors in kernel regression estimation
- Monte Carlo response surfaces: A comparative approach
- Bandwidth selection in nonparametric regression with general errors
- Comparison of bandwidth selectors in nonparametric regression under dependence
- Fitting a bivariate additive model by local polynomial regression
- Robust plug-in bandwidth estimators in nonparametric regression
- Minimum negative exponential disparity estimation in parametric models
- Piecewise convex function estimation: Pilot estimators
- Nonparametric regression with correlated errors.
- Normal approximation rate and bias reduction for data-driven kernel smoothing estimator in a semiparametric regression model
- Convergence rate for cross-validatory bandwidth in kernel hazard estimation from dependent samples
- On discrete Epanechnikov kernel functions
- Nonparametric estimation of dynamic discrete choice models for time series data
- On selection of statistics for approximate Bayesian computing (or the method of simulated moments)
- Joint sufficient dimension reduction for estimating continuous treatment effect functions
- Asymptotic comparison of (partial) cross-validation, GCV and randomized GCV in nonparametric regression
- Effect of dependence on stochastic measures of accuracy of density estimators
- Asymptotic behavior of bandwidth selected by the cross-validation method for local polynomial fitting
- A note on smoothing parameter selection for penalized spline smoothing
- On bandwidth choice for density estimation with dependent data
- On bandwidth selection problems in nonparametric trend estimation under martingale difference errors
- Sample selection models with monotone control functions
- Robustness by reweighting for kernel estimators: an overview
- Preprocessing noisy functional data: a multivariate perspective
- Estimation and inference for the counterfactual distribution and quantile functions in continuous treatment models
- On robust cross-validation for nonparametric smoothing
- Cross validation for locally stationary processes
- Nonparametric estimation of conditional quantile functions in the presence of irrelevant covariates
- A note on cumulative mean estimation
- Time-varying nonlinear regression models: nonparametric estimation and model selection
- Consistency of cross-validation when the data are curves
- Cross-validation in nonparametric regression with outliers
- From finite sample to asymptotics: a geometric bridge for selection criteria in spline regression
- A note on the optimality of generalized cross-validation bandwidth selection in partially linear models with kernel smoothing estimator
- Consistency of cross validation for comparing regression procedures
- Robustness of one-sided cross-validation to autocorrelation
- Nonparametric regression function estimation with surrogate data and validation sampling
- M-cross-validation in local median estimation
- Bandwidth selection for smooth backfitting in additive models
- Nonparametric regression penalizing deviations from additivity
- A Bayesian approach to bandwidth selection for multivariate kernel regression with an application to state-price density estimation
- Consistent model specification tests based on \(k\)-nearest-neighbor estimation method
- Determination of the smoothing parameter of an unbiased estimator of the efficiency function in the dose-effect relationships
- Nonparametric estimation of regression functions with both categorical and continuous data
- Convergence rates for average square errors for kernel smoothing estimators
- Model robust regression: combining parametric, nonparametric, and semiparametric methods
- Blind nonparametric regression
- Smooth varying-coefficient estimation and inference for qualitative and quantitative data
- Estimating subject-specific dependent competing risk profile with censored event time observa\-tions
- A change-point estimator using local Fourier series
- Central limit theorems for nonparametric estimators with real-time random variables
- Bootstrap selection of bandwidth and confidence bands for nonparametric regression
- Estimation of a regression spline sample selection model
- A cautionary note about crossvalidatory choice
- A Flexible and Fast Method for Automatic Smoothing
- THE UNIQUENESS OF CROSS-VALIDATION SELECTED SMOOTHING PARAMETERS IN KERNEL ESTIMATION OF NONPARAMETRIC MODELS
- Cross‐validation and non‐parametric k nearest‐neighbour estimation
- Smoothing parameter selection in quasi-likelihood models
- Bandwidth selection in robust smoothing
- Modification for boundary effects and jump points in nonparametric regression
- NONPARAMETRIC ESTIMATION OF REGRESSION FUNCTIONS WITH DISCRETE REGRESSORS
- Kernel‐based Generalized Cross‐validation in Non‐parametric Mixed‐effect Models
- Smoothing for small samples with model misspecification: Nonparametric and semiparametric concerns
- KERNEL REGRESSION SMOOTHING OF TIME SERIES
- A test of normality using nonparametrlic residuals
- Optimal asymptotic quadratic error of nonparametric regression function estimates for a continuous-time process from sampled-data
- Smoothing spline growth curves with covariates
- The asymptotic average squared error for polynomial regression
- Some automated methods of smoothing time-dependent data
- A nonlinear gaussian filter applied to images with discontinuities
- Smoothing Parameter Selection for Power Optimality in Testing of Regression Curves
- Exact risk approaches to smoothing parameter selection
- A simple root n bandwidth selector for nonparametric regression
- REGRESSION SMOOTHING PARAMETER SELECTION USING CROSS RESIDUALS SUM
- Local linear extrapolation
- Nonparametric regression for nonstationary processes
- An overview of model-robust regression
- Automatic bandwidth selection in robust nonparametric regression
- DOUBLE SMOOTHING ESTIMATION OF THE MULTIVARIATE REGRESSION FUNCTION IN NONPARAMETRIC REGRESSION
- ASYMPTOTIC STABILITY OF THE OSCV SMOOTHING PARAMETER SELECTION
- New view on smoothing parameter selector in function estimation
- On the estimation of prediction errors in logistic regression models
- A plug-in technique in nonparametric regression with dependence
- Fitting smoothing splines to data from multiple sources
- Binned modified cross–validation with dependent errors
- Global adaptive smoothing regression
This page was built for publication: How Far Are Automatically Chosen Regression Smoothing Parameters From Their Optimum?
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3787299)