Our study design includes two intervention groups and three repeated measurements (baseline, 4 weeks, final visit). To control for correlated observations per subject per visit, the analysis of outcomes will be by linear mixed model regression. This model will include the treatment covariate, the visit covariate and their interaction term and a random term to control for within-subject correlation. The primary outcome variable is change in body weight. The interaction term will indicate change over time in body weight by intervention group. Depending on the pattern of missing observations and loss to follow-up, missing values will be handled with multiple imputations or model approaches (including linear mixed models which are robust to missing observations), and sensitivity analyses will be performed as recommended [40, 41].

We expect that there will be treatment heterogeneity indicating that effects may differ depending on covariate values at baseline. For example, baseline body weight is highly predictive and correlated to body weight change during an intervention. All models will thus be adjusted for the baseline values of the outcome variable. In addition, the models will be adjusted for the blocking factor used in randomization.

The analyses will be performed according to the intention-to-treat approach, but per-protocol (in which noncompliant participants are excluded) analyses will also be reported as recommended by the CONSORT guidelines [21].

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.