Irregular simplex

The local area of interest in the diagram may be an irregular simplex with unknown vertex coordinates ... 

The experimental regions we have treated, when in the form of a simplex, have had the same shape as the total factor space. Thus they have been equilateral triangles, regular tetrahedra, etc. However this is not a necessary limitation. Any point in an irregular simplex, like the simplex of figure 9.17a, may be defined in terms of a mixture of the pseudocomponents at eaeh of the vertices. A response may then be analysed within that simplex by means of the Scheffe models and designs. This approach was used by the authors of references (7) and (8). 

FIGURE 8.10 Constrained region in three-component mixtures, (a) The feasible region (bold lines) shaped as inverted simplex lies entirely within the original simplex, (b) Part of the inverted simplex lies outside the feasible region (bold lines) and has irregular shape. 

Relational constraints may also give rise to irregularly shaped simplexes, which can be a basis for using the Scheffe experimental designs. For example, figure 9.17b shows the domain defined by the relationship ... 

Discrimination between hydrocarbons occurs during uptake. Blumer et al. (1970) found that among various species of copepods, Rhincalanus was the only species to accumulate n-C2i 6. Boutry et al. (1977) showed that the uptake of hydrocarbons by the diatom Chaetoceros calcitrans simplex was irregular and depended upon the age of the cultures and the composition of the medium. Bioaccumulation has been invoqued by Murray et al. (1977) to explain the enrichment of long-chain aliphatic hydrocarbons in mixed plankton. 

The Simplex method represents a more efficient approach using only function values for constructing an irregular polyhedron in parameters space, and moving this polyhedron towards the minimum, while allowing the size to contract or expands to improve the convergence. It is better than the simple-minded one-variable-at-a-time approach, but becomes too slow for many-dimensional functions. 

---