A note on the empirical likelihood confidence band for hazards ratio with covariate adjustment

摘要: In medical studies comparing two treatments in the presence of censored data, stratified Cox model is an important tool that has ability to flexibly handle non-proportional hazards while allowing parsimonious covariate adjustment. order capture cumulative treatment effect, ratio specific baseline often used as a measure effect. Pointwise and simultaneous confidence bands associated with estimated provide global picture how effect evolves over time. Recently, Dong Matthews (2012, Biometrics 68, 408-418) proposed construct pointwise interval for using plug-in type empirical likelihood approach. However, their result on limiting distribution generally incorrect resulting asymptotically undercovering. this article, we derive correct statistic. We also present simulation demonstrate effectiveness our