The desirability function is widely used in engineering field to tackle the problem of optimizing multiple responses simultaneously. This dissertation proposes an augmented desirability function that accounts for various additional information aiming to improve the practicality of the optimal solutions. The augmented desirability function can reduce the variation of predicted responses, as well as balance location and dispersion effects in a robust design study. The benefits of the augmented approach are demonstrated via real engineering examples. In addition, the desirability function is applied to a clinical trial for scleroderma patients for measuring patients' disease improvement.