survival.svb: Fit High-Dimensional Proportional Hazards Models
Implementation of methodology designed to perform: (i) variable
selection, (ii) effect estimation, and (iii) uncertainty quantification,
for high-dimensional survival data. Our method uses a spike-and-slab prior
with Laplace slab and Dirac spike and approximates the corresponding
posterior using variational inference, a popular method in machine learning
for scalable conditional inference. Although approximate, the variational
posterior provides excellent point estimates and good control of the false
discovery rate. For more information see Komodromos et al. (2021)
<doi:10.48550/arXiv.2112.10270>.
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=survival.svb
to link to this page.