I implelemented a Gibbs sampler for Bayesian Lasso [1] in R.
Bayesian Lasso is a fully Bayesian approach for sparse linear regression by assuming independent Laplace (a.k.a. double exponential) priors for each regression coefficient.
Usage Example:
library(lars)
data(diabetes)
x <- scale(diabetes$x)
y <- scale(diabetes$y)
betas <- gibbsBLasso(x, y, max.steps = 100000)
R Code:
gibbsBLasso.R
References:
[1] Park, Trevor and Casella, George. The Bayesian Lasso. Journal of American Statistical Association. 103(482):681-686. 2008.