Table 1. Protocol of a Target Trial on ADHD Medication on Mortality in Individuals With ADHD and Emulation Using Observational Data.
Protocol component | Target randomized trial | Emulation using observational data |
---|---|---|
Eligibility criteria |
|
|
Treatment strategies |
|
|
Assignment procedures | Eligible individuals are randomly assigned to either strategy at baseline and are aware of the assigned strategy | Randomization is emulated by cloning eligible individuals and assigning each copy to 1 treatment strategy |
Follow-up period | Follow-up starts at treatment assignment and ends at death, loss to follow-up (emigration), or administrative end of follow-up (December 31, 2020, or 2 years after baseline), whichever occurs first | Same as the target trial |
Outcomes | All-cause and cause-specific mortality within 2 years after baseline | Same as the target trial |
Causal contrasts of interest | Effect of adhering to the treatment strategies (per protocol) during follow-up | Observational analogue of the per-protocol effect |
Analysis plan | Effect estimates are calculated from an inverse probability-weighted, pooled-logistic regression model, with censoring at deviation from the protocol and adjustment for baseline and postbaseline covariates | Same as the target trial, except that the analyses are conducted in an expanded data set that includes copies of each eligible individual |
Abbreviation: ADHD, attention-deficit/hyperactivity disorder.