Optimal designs for frequentist model averaging

DOI10.1093/BIOMET/ASZ036MaRDI QIDQ5859771zbMATH OpenOpenAlexWikidataFDO

Authors Kira Alhorn, Kirsten Schorning, Holger Dette

Publication date 20 April 2021

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.05234, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6690170

zbMATH Keywords

Bayesian optimal designlocal misspecificationmodel averagingmodel selectionmodel uncertainty

Mathematics Subject Classification ID

General nonlinear regression (62J02) Optimal statistical designs (62K05)

Abstract: We consider the problem of designing experiments for the estimation of a target in regression analysis if there is uncertainty about the parametric form of the regression function. A new optimality criterion is proposed, which minimizes the asymptotic mean squared error of the frequentist model averaging estimate by the choice of an experimental design. Necessary conditions for the optimal solution of a locally and Bayesian optimal design problem are established. The results are illustrated in several examples and it is demonstrated that Bayesian optimal designs can yield a reduction of the mean squared error of the model averaging estimator up to $45\mathrm{\%}$.

Recommendations

• Optimal designs for model averaging in non-nested models
• scientific article; zbMATH DE number 1104303
• Optimal weight choice for frequentist model average estimators
• A Bayesian A ‐Optimal and Model Robust Design Criterion
• Optimal Bayesian design applied to logistic regression experiments

Cited in

(7)

• Optimal designs for model averaging in non-nested models
• Optimal designs for comparing population curves in hierarchical models
• Least squares model averaging for two non-nested linear models
• Model uncertainty and model averaging in regression discontinuity designs
• A Bayesian A ‐Optimal and Model Robust Design Criterion
• Miscellanea. Updating the average efficiency factor in  -designs
• Optimizing designs in clinical trials with an application in treatment of epidermolysis bullosa simplex, a rare genetic skin disease

This page was built for publication: Optimal designs for frequentist model averaging

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5859771)