Model averaging with the hybrid model: An asymptotic study and demonstration. (April 2022)

• Record Type: Journal Article
• Authors: Wee Soh, Kian; Lumley, Thomas; Walker, Cameron; O'Sullivan, Michael
• Is Part Of: Statistical methods in medical research. Volume 31:Number 4(2022)
• Page Start: 658
• Page End: 672
• Publication Date: 2022-04
• Subjects: Model averaging -- hybrid model -- cross-validation -- asymptotic study -- simulation; Medicine -- Research -- Statistical methods -- Periodicals; Research -- Periodicals; Review Literature -- Periodicals; Statistics -- methods -- Periodicals; Médecine -- Recherche -- Méthodes statistiques -- Périodiques; 610.727
• DOI: 10.1177/09622802211041750
• Languages: English
• ISSNs: 0962-2802

Abstract

In this paper, we present a new model averaging technique that can be applied in medical research. The dataset is first partitioned by the values of its categorical explanatory variables. Then for each partition, a model average is determined by minimising some form of squared errors, which could be the leave-one-out cross-validation errors. From our asymptotic optimality study and the results of simulations, we demonstrate under several high-level assumptions and modelling conditions that this model averaging procedure may outperform jackknife model averaging, which is a well-established technique. We also present an example where a cross-validation procedure does not work (that is, a zero-valued cross-validation error is obtained) when determining the weights for model averaging.