Bayesian Decision-theoretic Methods for Parameter Ensembles with Application to Epidemiology

TL;DR

This paper evaluates various decision-theoretic methods for estimating parameter ensembles in Bayesian models, focusing on their ability to accurately approximate empirical quantiles, quartile ratios, and classification thresholds, with applications in epidemiology.

Contribution

It compares multiple ensemble estimation methods, including CB, WRSEL, GR, MLE, and posterior means, for their effectiveness in meeting diverse inferential goals in Bayesian hierarchical models.

Findings

WRSEL and CB ensembles perform well in quantile approximation.

Posterior means excel in mean estimation but less in quantile accuracy.

Threshold classification losses improve decision-making in epidemiological data.

Abstract

Parameter ensembles or sets of random effects constitute one of the cornerstones of modern statistical practice. This is especially the case in Bayesian hierarchical models, where several decision theoretic frameworks can be deployed. The estimation of these parameter ensembles may substantially vary depending on which inferential goals are prioritised by the modeller. Since one may wish to satisfy a range of desiderata, it is therefore of interest to investigate whether some sets of point estimates can simultaneously meet several inferential objectives. In this thesis, we will be especially concerned with identifying ensembles of point estimates that produce good approximations of (i) the true empirical quantiles and empirical quartile ratio (QR) and (ii) provide an accurate classification of the ensemble's elements above and below a given threshold. For this purpose, we review various decision-theoretic frameworks, which have been proposed in the literature in relation to the optimisation of different aspects of the empirical distribution of a parameter ensemble. This includes the constrained Bayes (CB), weighted-rank squared error loss (WRSEL), and triple-goal (GR) ensembles of point estimates. In addition, we also consider the set of maximum likelihood estimates (MLEs) and the ensemble of posterior means --the latter being optimal under the summed squared error loss (SSEL). Firstly, we test the performance of these different sets of point estimates as plug-in estimators for the empirical quantiles and empirical QR under a range of synthetic scenarios encompassing both spatial and non-spatial simulated data sets. Performance evaluation is here conducted using the posterior regret. Secondly, two threshold classification losses (TCLs) --weighted and unweighted-- are formulated and formally optimised. The performance of these decision-theoretic tools is also evaluated on real data sets.