Better together? Statistical learning in models made of modules

In modern applications, statisticians are faced with integrating heterogeneous data modalities relevant for an inference, prediction, or decision problem. In such circumstances, it is convenient to use a graphical model to represent the statistical dependencies, via a set of connected “modules”, each relating to a specific data modality, and drawing on specific domain expertise in their development. In principle, given data, the conventional statistical update then allows for coherent uncertainty quantification and information propagation through and across the modules. However, misspecification of any module can contaminate the estimate and update of others, often in unpredictable ways. In various settings, particularly when certain modules are trusted more than others, practitioners have preferred to avoid learning with the full model in favor of approaches that restrict the information propagation between modules, for example by restricting propagation to only particular directions along the edges of the graph. In this article, we investigate why these modular approaches might be preferable to the full model in misspecified settings. We propose principled criteria to choose between modular and full-model approaches. The question arises in many applied settings, including large stochastic dynamical systems, meta-analysis, epidemiological models, air pollution models, pharmacokinetics-pharmacodynamics, and causal inference with propensity scores.

Citation

P.E. Jacob, L.M. Murray, C.C. Holmes, C.P. Robert (2017). Better together? Statistical learning in models made of modules. url:https://arxiv.org/abs/1708.08719.

@Article{,
title = {Better together? Statistical learning in models made of modules},
author = {Pierre E. Jacob and Lawrence M. Murray and Chris C. Holmes and Christian P. Robert},
year = {2017},
url = {https://arxiv.org/abs/1708.08719}
}