Generating and improving orthogonal designs by using mixed integer programming

Generating and improving orthogonal designs by using mixed integer programming

0.00 Avg rating0 Votes
Article ID: iaor20118880
Volume: 215
Issue: 3
Start Page Number: 629
End Page Number: 638
Publication Date: Dec 2011
Journal: European Journal of Operational Research
Authors: , , ,
Keywords: programming: integer
Abstract:

Analysts faced with conducting experiments involving quantitative factors have a variety of potential designs in their portfolio. However, in many experimental settings involving discrete‐valued factors (particularly if the factors do not all have the same number of levels), none of these designs are suitable. In this paper, we present a mixed integer programming (MIP) method that is suitable for constructing orthogonal designs, or improving existing orthogonal arrays, for experiments involving quantitative factors with limited numbers of levels of interest. Our formulation makes use of a novel linearization of the correlation calculation. The orthogonal designs we construct do not satisfy the definition of an orthogonal array, so we do not advocate their use for qualitative factors. However, they do allow analysts to study, without sacrificing balance or orthogonality, a greater number of quantitative factors than it is possible to do with orthogonal arrays which have the same number of runs.

Reviews

Required fields are marked *. Your email address will not be published.