Statistical Analysis in Two Stage Randomization Designs in Clinical Trials

clinical trials;counting process;risk set;survival analysis;two stage randomization design

Guo, Xiang ; Daowen Zhang, Committee Member,John Monahan, Committee Member,Marie Davidian, Committee Member,Anastasios A. Tsiatis, Committee Chair,Guo, Xiang ; Daowen Zhang ; Committee Member ; John Monahan ; Committee Member ; Marie Davidian ; Committee Member ; Anastasios A. Tsiatis ; Committee Chair

University:North Carolina State University

关键词: clinical trials;    counting process;    risk set;    survival analysis;    two stage randomization design;   

Others  :  https://repository.lib.ncsu.edu/bitstream/handle/1840.16/5768/etd.pdf?sequence=1&isAllowed=y

美国|英语

来源: null

【 摘 要 】

Two-stage randomization designs are becoming more common in many clinical trials related to diseases such as cancer and HIV, where an induction therapy is given followed by a maintenance therapy depending on patients' response and consent. The main interest is to compare combinations of induction and maintenance therapies and to find the combination leading to the longest average survival time. However, in practice, the data analysis is typically conducted separately in two stages.In this Thesis, we tackle the problem based on treatment policies. We use the concepts of counting process and risk set as described by Fleming and Harrington (1991) to find weighted estimating equations whose solution gives an estimator for the cumulative hazard function which, in turn, is used to derive an estimator for the overall survival distribution under a treatment policy with right-censored data. We call this estimator as the Weighted Risk Set Estimator (WRSE). We show that the WRSE is consistent and asymptotically normally distributed. In addition to survival distribution estimation, we also consider the hypothesis testing problem. Since the log rank test is the common method for hypothesis testing in survival analysis, we propose a test statistic using an inverse weighted version of the log rank test. We use simulation studies to demonstrate theproperties of our method and use data from a clinical trial, Protocol 88923, conducted by the Cancer and Leukemia Group B (CALGB) to illustrate how to implement the method.