I am reading the original Bayesian Lasso paper, and its follow up; They look straightforward to implement, mainly because of the conditional posterior probability for the gibbs sampler; however, I like to know more about its math and derivations, e.g how $1/\tau_j^2, 1/\omega_j^2, \sigma^2|., \lambda$ are derived.

How can I calculate these conditional probabilities by myself ? May be it is too much to ask, if someone can do the whole math here, but can you point me to a more comprehensive document/book where I can see exactly how to derive them ?

  • $\begingroup$ Are you familiar with deriving full conditionals for a linear regression with a normal prior on $\beta$ and a gamma prior on the precision (or inverse gamma on the variance)? If not, then that is probably a good place to start before trying to figure out how to deal with a Laplacian prior in the lasso case. $\endgroup$
    – ilanman
    Dec 15, 2015 at 0:21


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.