Relative Efficiency of R² and B² in Regression Analysis for Calibration and Formulation

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.