Since missing values appeared to be related to other observed information, the MCAR condition did not hold and CCA was expected to be biased.
In all the domains, the largest percentage of missing value appeared in Intimacy, 2.0-2.7% in the 21th, 23th, 24th item.
If the missing value appeared at the end of the interval, the value from the day next to the missing value was used.
Samples for which a missing value appears for any of the two genes in question are not considered when calculating the correlation between the genes.
It is very likely for missing values to appear during the collection of multi-phase data with the same subject, and this frequently leads to problems such as small sample sizes and under-representation.
Missing values might appear in incomplete interview questionnaires, incomplete headache diaries, missed intervention sessions and/or due to dropouts.
There were very few missing values and these appeared to be missing completely at random and non-informative.
The scores computed using standard rules in responders only were compared to those obtained after imputation of all missing values: the differences appeared modest overall (<0.25 standard deviation) for all dimensions.
Missing values, or generalized inputs, can appear in otherwise precise data.
