With two missing responses, the mean simulated PAM was unchanged, but the minimum PAM was, on average, 3.2 points below the mean simulated PAM and the maximum PAM was, on average, 4.4 points above the simulated mean (with corresponding APEs of 5.4% and 7.8%).
With 12 missing responses, the simulated mean is a full 4 points higher than the true mean (61.2 versus 57.2), which results in an average APE of 7.3%.
For all other cases with missing responses, we performed mean imputation.
For individuals with four or fewer missing responses, a person-mean imputation technique based on the existing responses was utilized to develop a total score.
The majority of items have four or fewer missing responses in total, the mean number of missing responses being 0.12 (sd = 0.67) with a range of 0 to 9 (2.3%) patients that did not respond to a particular item.
Furthermore, data were described with respect to the percentage of missing responses, frequencies for the response options, mean, standard deviation and median for each item.
The overall mean of missing responses were: FES-I, 0.9%; FES(S), 1.0%; mSAFFE, 1.3%; and ABC, 6.9% (those that left the scales completely blank are not included in these numbers).
For the data description, the percentage of missing responses, the frequencies for the response options mean, standard deviation (SD) and median for each item were assessed (Table 3).
The mean, s.d., and frequency of missing responses were described for each item.
Missing responses on multi-item scales were imputed using mean substitution provided valid items were present for at least 80% of items.
