Post-selection inference for L1-penalized likelihood models
Methodology
2016-10-17 v3
Abstract
We present a new method for post-selection inference for L1 (lasso)-penalized likelihood models, including generalized regression models. Our approach generalizes the post-selection framework presented in Lee et al (2014). The method provides p-values and confidence intervals that are asymptotically valid, conditional on the inherent selection done by the lasso. We present applications of this work to (regularized) logistic regression, Cox's proportional hazards model and the graphical lasso.
Cite
@article{arxiv.1602.07358,
title = {Post-selection inference for L1-penalized likelihood models},
author = {Jonathan Taylor and Robert Tibshirani},
journal= {arXiv preprint arXiv:1602.07358},
year = {2016}
}
Comments
23 pages, 8 figures