A Variational Inference Algorithm for BKMR in the Cross-Sectional Setting

2018 
The identification of pollutant effects is an important task in environmental health. Bayesian kernel machine regression (BKMR) is a standard tool for inference of individual-level pollutant health-effects, and we present a mean field Variational Inference (VI) algorithm for quick inference when only a single response per individual is recorded. Using simulation studies in the case of informative priors, we show that VI, although fast, produces anti-conservative credible intervals of covariate effects and conservative credible intervals for pollutant effects. To correct the coverage probabilities of covariate effects, we propose a simple Generalized Least Squares (GLS) approach that induces conservative credible intervals. We also explore using BKMR with flat priors and find that, while slower than the case with informative priors, this approach yields uncorrected credible intervals for covariate effects with coverage probabilities that are much closer to the nominal 95% level. We further note that fitting BKMR by VI provides a remarkable improvement in speed over existing MCMC methods.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    10
    References
    0
    Citations
    NaN
    KQI
    []