Clinical trials are experiments tested on human to compare the effect of certain intervention. In early-stage trials, fewer number of patients are enrolled to get preliminary information on safety and efficacy. In late-stage trials, larger number of patients are randomized to further confirm the efficacy and safety.
In Chapter 2, we propose a family of designs for phase I oncology trials. In these trials, oncologists assign different patients at a varying range of dose levels to find the dose that gives the highest acceptable rate of dose-limiting toxicities, which will be the recommended dose for phase II trials. Our proposed design, which we denote the cohort-sequence design, addresses the deficiencies of the popular 3+3 design, while preserving its simplicity.
Late-stage randomized clinical trials might lack external validity when there are treatment-by-covariate interactions involving factors whose distribution in the population differ from that in the trial. In Chapter 3, we project the results from a trial to a population using post-stratification, and compare it with other approaches that use probabilities of trial inclusion. We use intention-to-treat estimate of the treatment effect, which focuses on the treatment effect of randomization on the outcome without considering compliance. In Chapter 4, we extend the interpolation approaches using instrumental variables estimation of the complier average causal effect, which is the treatment effect on the outcome restricted to those who adhere to assigned treatment. We apply these methods to the data from Lipids Research Clinics Coronary Primary Prevention Trial and New York School Choice Experiment.
Daniel F. Heitjan
Xinlei (Sherry) Wang
Number of Pages
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Li, Shuang, "Clinical Trial Design and Analysis" (2019). Statistical Science Theses and Dissertations. 9.