Taguchi's methods (Montgomery, 1997) study the parameter space based on the
fractional factorial arrays from DoE, called orthogonal arrays. Taguchi argues that it
is not necessary to consider the interaction between two design variables explicitly,
so he developed a system of tabulated designs which reduce the number of
experiments as compared to a full factorial design. An advantage is the ability to
handle discrete variables. A disadvantage is that Taguchi ignores parameter
interactions.