| ptycho-package {ptycho} | R Documentation |
Bayesian Variable Selection with Hierarchical Priors
Description
Bayesian variable selection for linear regression models using hierarchical priors. There is a prior that combines information across responses and one that combines information across covariates, as well as a standard spike and slab prior for comparison. An MCMC samples from the marginal posterior distribution for the 0-1 variables indicating if each covariate belongs to the model for each response.
Details
This package provides functions to carry out Bayesian model selection combining
different layers of information: across multiple traits or across multiple
variants in the same gene. The priors are described by Stell and Sabatti
(2015). To sample the posterior distribution for specified genotype and
phenotype matrices, use ptycho.
This package also provides functions to generate simulated data as in Stell and
Sabatti (2015); see createData and
web.stanford.edu/~lstell/ptycho/. Those datasets are not included in this
package because they have images about 20 MB or larger. Instead small data
objects are included for examples; see Data.
Functions for post-processing ptycho objects are described at
checkConvergence and PosteriorStatistics.
Author(s)
Laurel Stell and Chiara Sabatti
Maintainer: Laurel Stell <lstell@stanford.edu>
References
Stell, L. and Sabatti, C. (2015) Genetic variant selection: learning across traits and sites, arXiv:1504.00946.