Abstract:
|
The dose-response studies of a drug is important in clinical trials, pharmacology and toxicology research. In dose-response clinical studies, humans or animals are exposed to the drug which has some effect depending on the dose level, and efficacy and/or toxicity are often the primary endpoints to be evaluated to determine the effective and safe ranges of the drug. Typical clinical dose-response studies consist of the comparison of several doses of a drug against a control, and one of the primary goals is to identify the minimum effective dose (MED) and the maximum safe dose (MSD). Multiple comparison procedures have been one of the major techniques to analyze data from dose-response studies. We will discuss some multiple comparison techniques, which include multiple test procedures (closed testing procedures and testing procedures based on partition principle), and simultaneous confidence intervals under the monotonicity assumption. Monotonicity helps to avoid logical inconsistencies and as such is essential in multiple testing. Examples are given to illustrate and compare these different approaches using summary data from W¨ohr, M., Borta, A., and Schwarting, R. (2005).
|