However, the final set of items within the remaining four domains of the Stoma-QOL successfully defined a meaningful measurement instrument with excellent psychometric properties with regard to validity and reliability.
Next, we calculated the item locations of the remaining items, using the same software.
In the main analyses, we used the adjusted score which represents the mean item score of the remaining items for that section as proposed by Pahel et al [ 15].
Finally, item-rest correlations between individual items and the sum of the remaining items on a factor were calculated.
With the exception of these items, the remaining items consistently loaded on these factors across time.
For those with up to 30% missing responses, we imputed a score for the missing items as the average of the remaining items of the questionnaire.
Following phase E of the item reduction, the wording of the remaining items was adapted to maximise consistency of both item wording and response format.
Factor 1 included 11 of the 15 initially proposed items; the structure of the remaining factors was unaltered.
Table 1 shows Spearman rank correlation coefficients for each item with the total of the remaining items.
These statistics provide a measure of the correlation between an item and the sum of the remaining items in the scale, with low values (less than 0.2) [ 16] indicating that an item is not measuring the same construct as other items.
Spearman's rank correlation coefficients were computed for each of the 14 items with the total of the remaining 13 items and reported with 95% confidence intervals (CI) obtained by nonparametric bootstrap with 9999 bootstrap replications [ 23].
