The Bayesian Lasso
Trevor Park, George Casella · Journal of the American Statistical Association · 2008
The Lasso estimate for linear regression parameters can be interpreted as a Bayesian posterior mode estimate when the regression parameters have independent Laplace (i.e., double-exponential) priors. Gibbs sampling from this posterior is possible using an expanded hierarchy with conjugate normal priors for the regression parameters and independent exponential priors on their variances. A connection with the inverse-Gaussian distribution provides tractable full conditional distributions. The Bayesian Lasso provides interval estimates (Bayesian credible intervals) that can guide variable selection. Moreover, the structure of the hierarchical model provides both Bayesian and likelihood methods for selecting the Lasso parameter. Slight modifications lead to Bayesian versions of other Lasso-related estimation methods, including bridge regression and a robust variant.
Cited by 2,934 works. doi:10.1198/016214508000000337
Authors
References
- Regression Shrinkage and Selection Via the Lasso
- Bayesian Inference in Statistical Analysis.
- The Elements of Statistical Learning: Data Mining, Inference, and Prediction
- Least angle regression
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- A Statistical View of Some Chemometrics Regression Tools
- Variable Selection Via Gibbs Sampling
- A new approach to variable selection in least squares problems
- Asymptotics for lasso-type estimators
- Bayesian Variable Selection in Linear Regression