The Intensity index has been suggested by Bannister (1960) as a measure of
the amount of construct linkage. Bannister suggested that the score reflects
the degree of organization of the construct system under investigation
(Bannister & Mair, 1968). The index resulted from his and his colleagues work
on construction systems of patient suffering schizophrenic thought disorder.
The concept of intensity has a theoretical connection to the notion of
"tight" and "loose" construing as proposed by Kelly (1991). While tight
constructs lead to unvarying prediction, loose constructs allow for varying
predictions. Bannister hypothesized that schizophrenic thought disorder is
liked to a process of extremely loose construing leading to a loss of
predictive power of the subject's construct system. The Intensity score as a
structural measure is thought to reflect this type of system disintegration
(Bannister, 1960).
Implementation as in the Gridcor program and explained on the
correspoding help pages:
"... the sum of the squared values of the correlations
of each construct with the rest of the constructs, averaged by the total
number of constructs minus one. This process is repeated with each
element, and the overall Intensity is calculated by averaging the
intensity scores of constructs and elements."
https://www.ub.edu/terdep/pag/man11.html.
Currently the total is calculated as the unweighted average of all
single scores (for elements and construct).