In the 1990s Cambridge ESOL began producing examinations using banks of items whose difficulty had been calculated using Item Response Theory combined with Rasch analysis techniques (Weir [2005]).
The process is to check for similarity among the items which is calculated using item features first, and then, based on those similarity, the CBF generates recommendations for the target user.
The composite health scores were calculated using item response theory with a partial credit model (12).
A total knowledge score for each patient was calculated, using the items that were retained after the item retention and deletion process.
An index of SES was calculated using the items regarding parent's education and occupation.
An SDI summary score was calculated using 16 items from the scale and dichotomised using a score below 10too indicate 'no difficulties' and a score of 10 or more to indicate 'some difficulties'.
Areas were calculated using the ITEM-software (Olympus).
For the quantitative analysis, after initial combination of the items' scores from the two sessions (if there were two), the mean and standard deviation of each theme for all universities were calculated using its subset items' score; items were simply weighted the same.
Provided at least half of the items in the scale were completed, the scale score was calculated using only those items for which values existed.
An overall quality of life score was calculated using all 39 items in the questionnaire.
