The effect of having two or more impairments compared to none was associated with lowered wellbeing after adjusting for demographic factors and social support (adjusted difference -2.37 on the well-being scale with SD = 7.9, p < 0.001) but after adjusting for disability the coefficient fell and was non-significant.
Since the intervention targeted MVPA and had no effect on sedentary behavior (adjusted difference between groups [Int-Ctl] = −2.81 mins/day; 95% CI [−21.74, 16.19]; P = 0.87) the intervention and control groups were combined for all analyses.
We used multiple logistic regression analysis with education as a covariate to adjust for group differences on this latter variable, as in this subset of women there was a significant difference between groups on education.
†Change associated with MA health reform obtained from difference-in-differences Poisson regression model to adjust for difference secular changes (based on comparison with New Jersey, New York, and Pennsylvania) with fixed effects for quarter and state.
We adjust for differences in demographics and socioeconomic status on a concurrent base, and prospectively adjust for differences in health [ 20].
Multivariate analysis was used to adjust for differences in patient characteristics at various levels of medical care on anticoagulation strategy.
Logistic regression was used to examine the association of OPCAB grafting with in-hospital adverse events after adjusting for differences between patients on the basis of each of the above-mentioned preoperative variables.
The first sensitivity analysis adjusted for significant baseline differences on demographic and clinical predictors of missing values.
All models were adjusted for significant group differences on the socio-demographic variables and included the four PSP domains as independent variables.
We will calculate adjusted mean differences in treatment effects on the outcome measure at 4-months using analysis of covariance.
e. Probabilities based on discontinuation rates, regardless of treatment, from data pooled from seven randomised placebo-controlled trials of atomoxetine [ 38- 42] (some are data on file), adjusted for differences between trials with respect to duration of follow-up.
