The use of experimental design in separation science

Abstract

In this tutorial, the application of experimental designs in separation science is discussed. Method optimization is often divided into screening and optimization phases. In the screening step, many factors, potentially affecting the separation, are screened to identify those with the largest effects. These are then further examined in an optimization phase, to determine the best separation conditions. After optimizing the method, it should be validated, before use for quantitative purposes. Robustness testing is part of method validation and examines the effects on the responses of small changes in method conditions. During the first phase of method optimization and during robustness testing, so-called screening designs are usually applied, whereas during the second phase of optimization, response-surface designs are often used. In this tutorial, the different steps in the application of both types of design are explained and elaborated with some examples.

Design of experiments applications in bioprocessing: Concepts and approach

“…Elimination of insignificant factors in the first step helps in reduction of experimental effort required in the second step. Screening designs such as Plackett-Burman (PB), [1][2][3][4] two level factorial, 1-3 fractional factorial, [1][2][3][5][6][7][8] and in some cases supersaturated designs 9 have been widely used. For precise prediction of the response surface, designs including the Box-Wilson central composite (CC), [10][11][12] Box-Behnken (BB), [13][14][15] and three level full-facto-rial [16][17][18] have been commonly used.…”

Coextraction of acidic, basic and amphiprotic pollutants using multiwalled carbon nanotubes/magnetite nanoparticles@polypyrrole composite

“…270 Subsequently, 1 g of sodium perchlorate was added to the mixture and stirred for 10 min. response is optimum when it is maximized, minimized, or at a predefined value [50].…”

Factorial Design and Machine Learning Strategies: Impacts on Pharmaceutical Analysis

“…Classification of CC designs depends on the value of alpha (α) or the distance between the axial points and the centre. Three types of CC design then exist: circumscribed (CCC), inscribed (CCI) and face-centred (CCF) [1,13,[23][24][25][26].…”

“…For ANOVA to be properly conducted, the response variable has to be continuous and at least one of the investigated variables is categorical. For a factor to be significant, the p-value is usually less than α of 0.05 [1,[23][24][25][26].…”