Multivariate logistic regression was used to analyse the odds of hip fracture in patients using FRIDs in all analyses.
To analyse the odds of hip fracture in patients using FRIDs we created four different models for each FRID.
For each FRID we also analysed the odds of hip fracture in combined multimorbidity level groups, RUBs 0 2 and RUBs 3 5, adjusted for age and gender.
After matching, we used logistic regression to analyse the odds of outpatient service utilization and self-treatment utilization among individuals reporting chronic illness, acute illness, and chronic illness with an acute episode, with and without MIP.
We applied the random-effect model to directly analyse the pooled odds ratios of methylation associated with pathological stage, Gleason score, and PSA levels.
Univariate logistic regression was used to analyse the crude odds ratios for dystocia in relation to various background- and lifestyle characteristics and self-reported history of violence.
Differences in binary prevalence variables were analysed as the odds ratio between post-implementation and baseline.
Since the event rates are low across the treatment groups and subset analyses, the odds ratio (OR) is used to estimate the relative risk (RR) and the treatment group effect is described in terms of risk instead of odds.
In these analyses, the odds ratio from each study was regressed on the potential confounders in univariable and multivariable weighted linear regressions weighted according to the inverse standard error and the residual between-trial variance.
From adjusted and unadjusted analyses, the odds of women returning for their results was not significantly associated with maternal age, education, number of previous live births, or HIV status.
