期刊
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
卷 82, 期 12, 页码 1767-1774出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/00949655.2011.595010
关键词
time-on-study; baseline age; left truncation; cumulative hazard; time scale; time-to-event; age-at-entry
The Cox proportional hazards model is widely used in time-to-event analysis. Two time scales are used in practice: time-on-study and chronological age. The former is the most frequently used time scale in clinical studies and longitudinal observation studies. However, there is no general consensus about which time scale is the best. It has been asserted that if the cumulative baseline hazard is exponential or if the age-at-entry is independent of the covariate, then the two models are equivalent. We show that neither of these conditions leads to equivalency. Variability in the age-at-entry of individuals in the study causes the models to differ significantly. This is shown both analytically and through a simulation study. Additionally, we show that the time-on-study model is more robust to changes in age-at-entry than the chronological age model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据