I have a regression model with regression coefficients $\beta_j$, $j=1,...,n$, and I would like to use a LASSO prior for $\beta_j$, this is:

$$\beta_j \sim Laplace(0,1/\lambda),$$

where the Laplace density function is $\pi(\beta_j\vert b) = \dfrac{1}{2b}\exp\left(-\dfrac{\vert \beta_j \vert}{b}\right)$. What priors are typically used in the literature for $\lambda$? I was thinking of using a "non informative" Gamma or Inverse Gamma, but I wanted to check if there are some better choices?


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.