† Difference (95% CI) of mean between intervention and control groups adjusted by type of facility (centre or post), and age (continuous variable), degree (MSc/BSC in midwifery or others) of participants, and being in-charge or not (only for comparing all providers).
Table 4 shows the results when comparing the prevalence of dosing inadequacy and DRPs per patient between the control and intervention groups adjusted by age, diastolic blood pressure, creatinine, number of total drugs and comorbidity: T2DM.
The general lineal model was used to compare the neuropsychological tests between the three groups adjusting by age and depression, when necessary.
Data will be analysed on an intention-to-treat basis, comparing changes at each time point between groups, adjusting for baseline values by analysis of covariance.
Allele- and genotype frequencies between groups were compared by the χ2 test or by Fisher's exact test whereas multiple regression was used to compare clinical variables between groups, adjusting for age, sex and BMI.
Second, whereas the imbalances in clinical characteristics between groups were adjusted by multivariate analyses, residual confounding may be present.
Multiple comparisons between the four groups were adjusted by a simulation-based approach in the same mixed model procedure.
However, when there are large differences in the distribution of covariates between the groups, adjusting for these differences by conventional regression may result in residual bias and limit causal inference.
The subgroup comparisons between the well, moderate, and poor groups with the normal group were adjusted by the Bonferroni method.
a) P values for effect of intervention between groups (repeated-measurements ANOVA adjusted by baseline values).
