Bayesian Hierarchical Invariant Prediction
By: Francisco Madaleno , Pernille Julie Viuff Sand , Francisco C. Pereira and more
Potential Business Impact:
Finds what truly causes things, even with lots of data.
We propose Bayesian Hierarchical Invariant Prediction (BHIP) reframing Invariant Causal Prediction (ICP) through the lens of Hierarchical Bayes. We leverage the hierarchical structure to explicitly test invariance of causal mechanisms under heterogeneous data, resulting in improved computational scalability for a larger number of predictors compared to ICP. Moreover, given its Bayesian nature BHIP enables the use of prior information. In this paper, we test two sparsity inducing priors: horseshoe and spike-and-slab, both of which allow us a more reliable identification of causal features. We test BHIP in synthetic and real-world data showing its potential as an alternative inference method to ICP.
Similar Papers
A Bayesian Integrative Mixed Modeling Framework for Analysis of the Adolescent Brain and Cognitive Development Study
Methodology
Finds brain patterns linked to behavior.
Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization
Statistics Theory
Finds true causes, not just patterns.
Robust Bayesian high-dimensional variable selection and inference with the horseshoe family of priors
Methodology
Finds important data even with messy numbers.