Exracting additional knowledge and performance from a configurational model that already has wide coverage

 

A decision tree algorithm, as available within EvalC3, can generate a classification tree  (a set of predictive models) of the kind shown here.

Some of the models (each branch is a model) are very detailed (i.e. has lots of attributes) and have narrow coverage. Such as HasQuotas+NotPost Conflict Situation+High Level of Human Development+ Low Womens Status = Low levels of womens representation in Parliament, which covers two cases (Senegal, Tanzania). 

Others are quite simple, with only two or three attributes and can have much wider coverage. Such as HasQuotas+ IsPostConflict = High levels of womens representation in Parliament, which covers two six cases (Burundi, Ethiopia, Mozambique, Namibia, South Africa, Uganda)

These wide coverage models may have unexplored potential, in the form of unexploited information content within the cases they cover. The raw (i.e. numerical) outcome data for the cases they cover only can be examined and recalibrated i.e re-dichotomised into two new sub-groups representing relatively higher versus lower outcome values within that set only. 

A new configurational analysis can then focus on that sub-set of cases to see if (a) any of the pre-existing attrubutes could predict membership of the two sub-groups, or (b) if any additional attributes, based on other knowledge of these cases, could do so.The ability to predict such finer grained performance differences would be a significant improvement.

This analytic step is a complementary move to that known as "pruning", where the removal of a mode attribute improves coverage, at the cost of precision.  Here an extra attribute is sought that will improve precision but at the cost of coverage. Perhaps it could be called "grafting"...

Postscript: But how significant will this addition to the model be? If, as above, there are six cases involved, there are 2^6 possible binary groupings of these case i.e 32. So any one grouping of two sets of cases has a 1/32 or 3.125% chance of occuring randomly (if the cases are causally independent).