Gamel J W, Vogel R L
Veterans Administration Medical Center, Louisville, Kentucky, USA.
Stat Med. 1997 Jul 30;16(14):1629-43. doi: 10.1002/(sici)1097-0258(19970730)16:14<1629::aid-sim594>3.0.co;2-c.
We derived three parametric survival models (the log-normal, log logit, and Weibull) from the clinical data of chemotherapy trials for stage II breast cancer. We then used these models to generate simulated survival data, which we analysed using both parametric (log-normal) and non-parametric (logrank, Gray-Tsiatis and Laska-Meisner) methods. With limited follow-up (5 years), the non-parametric tests had greater power than the log-normal model. This advantage diminished, however, with extended follow-up (15 years). Furthermore, only the log-normal model could distinguish reliably a survival advantage due to an increase in cured fraction from an advantage due to an increase in time to failure.
我们从II期乳腺癌化疗试验的临床数据中推导了三种参数生存模型（对数正态模型、对数logit模型和威布尔模型）。然后，我们使用这些模型生成模拟生存数据，并分别采用参数方法（对数正态法）和非参数方法（对数秩检验、Gray-Tsiatis检验和Laska-Meisner检验）进行分析。在随访期有限（5年）的情况下，非参数检验的效能高于对数正态模型。然而，随着随访期延长（15年），这种优势逐渐减弱。此外，只有对数正态模型能够可靠地区分因治愈比例增加导致的生存优势和因至失败时间增加导致的生存优势。
