An algorithmic technique for constructing optimal design for biased models. – S. S. Akpan and E. E. Williams
January 18, 2021Journal Vol6_No.1&2
ABSTRACT
An algorithm to locate the global minimum of the alias matrix for the biased response function has been developed. The algorithm begins by classifying all the support points into experimental region of interest, then starting from an arbitrary set of N support points, the algorithm obtains an N – point optimal design by systematically adding and dropping support points from the various groups in such a way that alias matrix of the design at each step of the sequence is reduced. A UML diagram is provided for the algorithm which gives a free flow with application of numerical values.