Title: Debiasing the debaised lasso with bootstrap
Authors: Sai Li - University of Pennsylvania (United States) [presenting]
Abstract: It is proven that under proper conditions, bootstrap can further correct the bias of the debiased lasso estimator for statistical inference of low-dimensional parameters in high-dimensional linear regression. We prove that the required sample size for inference with bootstrapped debiased lasso, which involves the number of small coefficients, can be of smaller order than the existing ones for the debiased lasso. Therefore, our results reveal the benefits of having strong signals in high-dimensional inference. Our theory is supported by results of simulation experiments, which compare coverage probabilities and lengths of confidence intervals with and without bootstrap, with and without debiasing.