Confidence intervals for high-dimensional Cox models

The purpose of this paper is to construct confidence intervals for the regression coefficients in high-dimensional Cox proportional hazards models where number covariates may be larger than sample size. Our debiased estimator construction similar those Zhang and (2014) van de Geer et al. (2014), but time-dependent censored risk sets introduce considerable additional challenges. theoretical results, which provide conditions under our are asymptotically valid, supported by extensive numerical experiments.