On Bayesian lasso variable selection and the specification of the shrinkage parameter
We propose a Bayesian implementation of the lasso regression that accomplishes both shrinkage and variable selection. We focus on the appropriate specification for the shrinkage parameter λ through Bayes factors that evaluate the inclusion of each covariate in the model formulation. We associate this parameter with the values of Pearson and partial correlation at the limits between significance and insignificance as defined by Bayes factors. In this way, a meaningful interpretation of λ is achieved that leads to a simple specification of this parameter. Moreover, we use these values to specify the parameters of a gamma hyperprior for λ. The parameters of the hyperprior are elicited such that appropriate levels of practical significance of the Pearson correlation are achieved and, at the same time, the prior support of λ values that activate the Lindley-Bartlett paradox or lead to over-shrinkage of model coefficients is avoided. The proposed method is illustrated using two simulation studies and a real dataset. For the first simulation study, results for different prior values of λ are presented as well as a detailed robustness analysis concerning the parameters of the hyperprior of λ. In all examples, detailed comparisons with a variety of ordinary and Bayesian lasso methods are presented.
KeywordsBayes factors MCMC Gamma hyperprior for λ Partial correlation Pearson correlation Shrinkage Benchmark and threshold correlations
Unable to display preview. Download preview PDF.
- Armagan, A., Dunson, D., Lee, J.: Bayesian generalized double Pareto shrinkage. arXiv:1104.0861v3 [stat.ME] (2012)
- Balakrishnan, S., Madigan, D.: Priors on the variance in sparse Bayesian learning: the demi-Bayesian lasso. In: Chen, M.-H., Muller, P., Sun, D., Ye, K. (eds.) Frontiers of Statistical Decision Making and Bayesian Analysis: In Honor of James O. Berger, pp. 346–359. Springer, Berlin (2010) Google Scholar
- Gramacy, R.: monomvn: Estimation for multivariate normal and Student-t data with monotone missingness. R package version 1.8-3 (2010) Google Scholar
- Li, Q., Lin, N.: The Bayesian elastic net. Bayesian Anal. 5, 847–866 (2010) Google Scholar
- R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2011) Google Scholar
- Scheipl, F.: Normal-mixture-of-inverse-gamma priors for Bayesian regularization and model selection in structured additive regression models. Technical Report 84, Department of Statistics, University of Munich (2010); available at http://epub.ub.uni-muenchen.de/11785/
- Scheipl, F.: Spikeslabgam: Bayesian variable selection, model choice and regularization for generalized additive mixed models in R. J. Stat. Softw. 43(14), 1–24 (2011) Google Scholar
- Zellner, A.: On assessing prior distributions and Bayesian regression analysis using g-prior distributions. In: Goel, P., Zellner, A. (eds.) Bayesian Inference and Decision Techniques: Essays in Honor of Bruno de Finetti, pp. 233–243. North-Holland, Amsterdam (1986) Google Scholar