In this thesis, contributions are made towards improving the design, conduct and analysis of multi-arm multi-stage clinical trials. First, we generalize the Dunnett (1955) test to derive efficacy and futility boundaries for a multi-arm multi-stage clinical trial. We show the boundaries control the familywise error rate in the strong sense. The method is applicable for any number of treatment arms, number of stages and number of patients per treatment per stage. It can be used for a wide variety of boundary types or rules derived from a-spending functions. Additionally, we show how sample size can be computed under a least favourable configuration power requirement and derive formulae for expected sample sizes. Next, we describe a general method for finding a confidence region for a vector of K unknown parameters that is compatible with the decisions of a two-stage closed testing procedure in an adaptive experiment. The closed test procedure is characterized by the fact that rejection or nonrejection of a null hypothesis may depend on the decisions for other hypotheses and the compatible confidence region will, in general, have a complex, nonrectangular shape. We find the smallest Cartesian product of simultaneous confidence intervals containing the region and provide computational shortcuts for calculating the lower bounds for parameters corresponding to the rejected null hypotheses. We illustrate the methodology with a detailed example of an adaptive Phase II/III clinical trial. Finally, using the combination test principle and the conditional error principle, we develop flexible sequential designs for multi-arm clinical trials with early stopping for efficacy and futility. Such designs have the flexibility to cope with a large range of exigencies that may occur in practice. They also have the advantage that test decisions are based on sufficient statistics if the trial proceeds as originally planned.