In p >> n settings, full posterior sampling using existing Markov chain Monte Carlo (MCMC) algorithms is highly inefficient and often not feasible from a practical perspective. To overcome this problem, we propose a scalable stochastic search algorithm that is called the Simplified Shotgun Stochastic Search (S5) and aimed at rapidly explore interesting regions of model space and finding the maximum a posteriori(MAP) model. Also, the S5 provides an approximation of posterior probability of each model (including the marginal inclusion probabilities). This algorithm is a part of an article titled Scalable Bayesian Variable Selection Using Nonlocal Prior Densities in Ultrahigh-dimensional Settings (2017+), by Minsuk Shin, Anirban Bhattachary, and Valen E. Johnson, accepted in Statistica Sinica.
|Depends:||R (≥ 3.2.4)|
|Imports:||Matrix, stats, snowfall, abind|
|Author:||Minsuk Shin and Ruoxuan Tian|
|Maintainer:||Minsuk Shin <minsuk000 at gmail.com>|
|License:||GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]|
|CRAN checks:||BayesS5 results|
|Windows binaries:||r-devel: BayesS5_1.30.zip, r-release: BayesS5_1.30.zip, r-oldrel: BayesS5_1.30.zip|
|OS X Mavericks binaries:||r-release: BayesS5_1.30.tgz, r-oldrel: BayesS5_1.30.tgz|
|Old sources:||BayesS5 archive|
Please use the canonical form https://CRAN.R-project.org/package=BayesS5 to link to this page.