A0356
Title: Searching in ultra high dimensional sparse model spaces: New performance tests and boosting Gibbs sampling algorithms
Authors: Gonzalo Garcia-Donato - Department of Economics and Finance - Universidad de Castilla La Mancha - Instituto de Desarrollo Regional (Spain) [presenting]
Maria Eugenia Castellanos Nueda - Universidad Rey Juan Carlos (Spain)
Abstract: In the context of variable selection in sparse settings, a novel class of experiments is presented. These are based on the notion of contaminating real data sets with artificial spurious covariates in such a way that exact solutions can be easily computed. Such exact responses provide a direct and compelling way to evaluate the performance of search methods on model spaces of arbitrary cardinality. This tool is applied to Gaussian regression models, an important statistical problem that has benefited from the emergence of many new search methods in recent years. The contribution is also via revisiting classical Gibbs sampling algorithms, proposing new implementations that take advantage of sparsity. Despite their simplicity, the resulting methods are very competitive and fully automatic. A real genetic dataset is used to illustrate and motivate the various procedures presented in this research.
