For data measured on the interval scale (e.g., time to first success), a repeated measures analysis of variance was used.
For data measuring events (e.g. whether a gene has been found to be differentially expressed or not) we implement binomial test and Fisher's exact test.
MD will be used for data measured on the same scales and for which the same units are used.
Weighted mean differences will be used for data measured on the same scales and for which the same units are used; otherwise, standardised mean differences will be used.
For data measured at two time points (GP Confidence scale) regression analyses were conducted, in which the difference between groups were explored after adjusting for pre-test scores [ 30].
A much better model fit was obtained for these particles for data measured 36 h after preparation (Fig. 13, right panel).
For data measured at one time point (the GP Clinical assistance items) independent t-tests were employed to compare mean differences of complete cases between groups.
Weighted mean differences will be used for data measured on the same scale and for which the same units are used; otherwise, standardised mean differences will be used (http://www.cochrane.org/handbook).org/handbook
Finally, for data measured at three timepoints (GPAQ scales, TPS and Pathways to Care scale), mixed model analysis was employed, using the MIXED procedure in SPSS (consistent with methodology carried out in the primary outcomes article [ 14]).
The κ-statistic, which is appropriate for categorical data, measures the degree of agreement beyond chance.
