Delete or merge regressors for linear model selection
Abstract
We consider a problem of linear model selection in the presence of both continuous and categorical predictors. Feasible models consist of subsets of numerical variables and partitions of levels of factors. A new algorithm called delete or merge regressors (DMR) is presented which is a stepwise backward procedure involving ranking the predictors according to squared t-statistics and choosing the final model minimizing BIC. In the article we prove consistency of DMR when the number of predictors tends to infinity with the sample size and describe a simulation study using a pertaining R package. The results indicate significant advantage in time complexity and selection accuracy of our algorithm over Lasso-based methods described in the literature. Moreover, a version of DMR for generalized linear models is proposed.
Cite
@article{arxiv.1505.04008,
title = {Delete or merge regressors for linear model selection},
author = {Aleksandra Maj-Kańska and Piotr Pokarowski and Agnieszka Prochenka},
journal= {arXiv preprint arXiv:1505.04008},
year = {2015}
}