Problematic items were excluded based on the adopted criteria (MI ≥ 30; Brown 2006) and on methodological decisions detailed below.
This made them vulnerable to the accusation that they de-listed problematic items or 'closed' controversies over 'deeper' or 'broader' issues, as we have seen.
Both studies used a Portuguese-language version of the SWBQ, and both concluded that a model which excluded three problematic items offered the best fit to the data.
Following the review of these translations by Czech traffic psychologists, problematic items were identified (in terms of wording, ambiguity, and specific features of the Czech context), and these were then translated anew by another translator.
Based on these analyses of the Portuguese version, we opted to test two additional models, a four-factor oblique model without items 6, 8 and 9 (Model 5) and another similar model without these three problematic items but with error correlations between items 1 2, 4 5 and 17 19 (model 6).
The reliability of scales is moderate but satisfactory given their length (three items per each subscale) and improves after removing problematic items.2 All Grit items, except one, function well psychometrically and its subscales have comparable reliability (standardised Cronbach's alpha values 0.65 0.67).
Among the enhanced security measures will likely be tighter screening of carry-on items to allow Transport Security Administration agents to discern problematic items in tightly stuffed bags.
Because problematic items usually get merged in a late step of the ICLUST procedure, they can be more easily identified and they do not obscure the factorial structure as much as in an EFA (for more information, see [69]).
During each step, problematic items were identified.
This analysis also indicates possibly problematic items and or/subjects.
Problematic items were noted for discussion by the research team.
