Those covariates that were significantly related to self-rated health were included in multivariate models investigating the relationships between self-rated health, somatisation and service use.
Therefore, to account for potential confounding, the baseline value was added to the univariate and multivariate models investigating the association between changes from baseline HRQoL and OS.
A multivariate logistic regression model investigated the independent contribution of all covariates.
Two-way interactions between biological plausible and significant variables in the multivariate model were investigated.
Two-way interactions between biologically plausible variables in the multivariate model were investigated.
Multivariate regression models investigated differences in log-transformed cytokine concentrations (dependent variables), with increasing number of variables (model 1: unadjusted; model 2: sex and age adjusted; model 3: age, sex, and BMI [independent variables] adjusted) (Supplementary Table 2).
Using multivariate models, we investigated whether AUDIT categories were independently associated with the proximal and distal study outcomes, controlling for potential confounding factors.
The associations between the corneal biomechanical parameters with the anterior segment parameters through age- and gender-adjusted linear regression analyses and multivariate models were investigated.
We used quantitative DNA methylation analysis combined with multivariate modelling to investigate the relationships between nutritional, anthropometric and metabolic factors and the CGI methylation of 11 genes, together with LINE-1 as an index of global DNA methylation.
Independent factors found significant by Pearson's chi square analysis were all entered in one step, into four separate multivariate logistic regression models, investigating the likelihood of having decay, ≥ 18 SUNT, tooth wear, and periodontal pockets ≥ 4 mm.
