The test reliability, determined using a split-half correlation with Spearman-Brown correction, was 0.81.
Despite the small participant sample, the split-half correlation for the thus obtained data set was.7 (attenuated for length).
Cronbach's Alpha split-half correlation was calculated for the matrix.
We believe that this discrepancy is caused by the fact that a split-half correlation of a single activation pattern mostly depends on the much stronger common component, which was found to be smaller for trained than untrained sequences in our study, but slightly higher in the study by Huang et al., (2013).
The simplest way to determine the reliability of a variable is to calculate the split-half correlation and attenuate it for length, a method that has been applied for the FLP (Ferrand et al., 2010) and DLP (Keuleers, Diependaele, & Brysbaert 2010).
To further investigate whether the identified TSRs were not artifacts due to gene selection, we applied the split-half method to each TSR. Figure 1C shows the split-half correlations for the first 50 TSRs, which were high (>0.91), indicating their high internal consistency.
Inter-item correlations, split-half correlations and Cronbach's alpha were used to investigate reliability and internal consistency.
Split-half correlations were computed for all possible ways of combining observers into two groups (without replacement).
The reliability of QI scores will be evaluated by multiple bootstrapped spit-half correlations of patient samples and time-to-time correlations of repeated QI scores.
DOI: http://dx.doi.org/10.7554/eLife.00801.012 Here we did not find larger split-half correlations for the patterns associated with trained compared to untrained sequences.
STAI demonstrated good internal consistency in the present study with a Cronbach's alpha of 0.82 and split-half correlations of 0.81 for antenatal assessment.
