Abstract
The assessment of the adequacy of a regression equation, as measured by the degree of closeness of the predicted values and their respective observed values is accomplished by the two contending statistics, R2 and B2. The derivation of the two statistics is presented and their relative performances are examined in the context of several pharmaceutics experiments involving, calibration, validation and formulation. The results strongly indicate that the B2-statistic is much more sensitive and efficient than the R2-statistic which has a tendency to inflate the magnitude irrespective of the data structure.