Statistical methods for measuring and comparing treatment efficacies: applications to nude mice experimentation.

A method is proposed for measuring and comparing the growth over time of a sample of tumors subjected to a number of different therapies. The procedure, which is illustrated by means of an example, does not require explicit parametric modelling of the growth curve itself and is particularly useful when the comparison of treatment efficacies is of chief interest. In addition, an ad hoc approach to the estimation of required sample sizes is delineated.