Title: Intelligence Tests Restriction Matrix

Source: Borg and Groenen (2005)

Description: Two data sets below each other. The first one contains
the intercorrelations of eight intelligence tests. The intelligence
tests are coded on the facets ‘language’ = {N = numerical, G =
geometrical} and ‘requirement’ = {A = application, I = inference} as
indicated below. The second data set contains the hypothesized
restriction matrix for the intercorrelations of eight intelligence
tests. The proximities for items with the same structuples, such as
p(NA1,NA2) and p(GA1,GA3), all are set to the value ‘5’. The
proximities that correspond to the immediate neighborhood relations
are set to the value ‘4’, since none of these distances should be
larger than any distance between definitionally equivalent items.
Finally, the large distances between the groups NI, GA and the groups
NA, GI are set to ‘3’. The hypothesized data should be treated
ordinally, so that the values 3, 4, and 5 are immaterial and may be
replaced by any numbers that have the same order.

 Test  Language  Requirement
   1      N           A
   2      N           A
   3      N           I
   4      G           I
   5      G           I
   6      G           A
   7      G           A
   8      G           A