Description of the statistical aspects of a study for advanced colorectal cancer patients.

A screening design was used in a trial that compared a standard regimen to five experimental regimens for the treatment of advanced colorectal cancer where the endpoint was survival. The two-stage design permitted the termination of accrual to experimental regimens that failed to show promise at the first stage. It also allowed for termination of accrual to the standard regimen if an experimental regimen appeared to offer a highly significant improvement over the standard regimen. This paper presents a description of the design and the results of the trial.