Our experimental results on classical, fuzzy, weighted and temporal incomplete CSPs show that some of our algorithms are very good at finding a necessarily optimal solution while asking the user for only a very small fraction of the missing preferences.
For the analyses that used four-day mean preferences for each hydrolysate series, the fifth day's data was used in three cases when the individuals did not interact with the stimuli on one of the earlier days and consequently were missing a preference score for a day.
Missing food preference data were accounted for in the calculation of averages across categories.
For the subject's treatment preference at month 12, a one-sample test of proportions was employed with a null hypothesis of an equal (50%) preference for missing data and the "no preference" response excluded from the analysis.
* Some data missing; ** Japanese preference weights applied; # One-way ANOVA analysis.
The designer can select the final solution according to his/her preferences without missing the knowledge available from the set of optimal solutions.
Interestingly, patients' needs, wants and preferences are missing from the list.
It uncovers the importance of environmental affordances in green space preference studies, a topic that is largely missing from existing work on landscape preference.
* Data missing for one patient in preference group.
The three scales are significantly different as to number of response categories, patient and clinician preference, likelihood of missing data and administration requirements [ 1].
