Use of a more general model for bioavailability studies

Use of a multivariate model for bioavailability crossover studies is discussed. The model affords a convenient way to obtain from untransformed data exact confidence intervals and general hypothesis tests for ratios that are pertinent for comparing formulations. Previously, confidence intervals for the case of a two period study of two formulations have been presented. This paper treats the case of three or more formulations in a study in which each subject receives each formulation. The model requires weaker assumptions than the assumptions of other models that have been commonly used. In addition to inferences on ratios, it is pointed out how to obtain from the model tests of the hypotheses of equal formulation effects, equal period effects, and equal sequence effects. The use of these concepts for studies in which a formulation is received more than once by subjects isalso discussed.