Optimal Classification/Rypka Method/Equations/Separatory/Characteristic/Empirical/Target Set

Target Set Truth Table ValueEdit

$t_i = \sum_{j=0}^K v_{i,j} V^{(K-j)}$, where:[1]

• vi,j is the element's attribute value,
• i is the ith element's index value, where,
i = 0...G' where G is the number of elements in the bounded class, and,
• j is the j'th characteristic's index value, where,
j = 0...K and where,
• K is the number of characteristics in the target set,
• V is highest value of logic in the group,
• V(K-j) is the positional value of the jth characteristic.

$n_{t_i} = n_{t_i} + 1$, where,

nti contains the multiset count for each truth table value[2].

NotesEdit

1. As the characteristic with the greatest separatory value is moved to the next most significant position, K is incremented to expand the target set size from two characteristics to the number of characteristics in the group or the number of characteristics which result in 100% separation. For the initial target set with one characteristic the separatory value is computed individually for each characteristic in the group to find the initial characteristic with the highest separatory value.
2. coefficient of association, $coa = \frac{n_{t_i}}{n_R}$, see page 172 of the primary reference