Estimation of the optimal design of a nonlinear parametric regression problem via Monte Carlo experiments

Authors:
Ida Hertel;Michael Kohler
Affiliations:
-;-
Venue:
Computational Statistics & Data Analysis
Year:
2013

Citing 6
Cited 0

Exponential bounds of mean error for the nearest neighbor estimates of regression functions

Journal of Multivariate Analysis
Optimal exact experimental designs with correlated errors through a simulated annealing algorithm

Computational Statistics & Data Analysis
Nonparametric estimation of non-stationary velocity fields from 3D particle tracking velocimetry data

Computational Statistics & Data Analysis
Nonparametric regression estimation using penalized least squares

IEEE Transactions on Information Theory
The uniform convergence of nearest neighbor regression function estimators and their application in optimization

IEEE Transactions on Information Theory
Nonparametric estimation via empirical risk minimization

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.03

Visualization

Abstract

A Monte Carlo method for estimation of the optimal design of a nonlinear parametric regression problem is presented. The basic idea is to use Monte Carlo to produce values of the error of a parametric regression estimate for randomly chosen designs and randomly chosen parameters; then, using this data, nonparametric regression is used to estimate the design for which the maximal expected error with respect to all possible parameter values is minimal. A theoretical result concerning the consistency of the optimal design estimate is presented, and the method is used to find an optimal design for an experimental fatigue test.