 Randomist control trials can be complicated by non-compliance and missing outcomes to address these issues. One method is known as intention to treat it analysis. This involves including everyone who was randomly assigned to a treatment group in the analysis regardless of whether they followed through with their treatment or not. This ensures that the results are not skewed by non-compliance or other factors. Additionally, ITT analysis ignores protocol deviations, withdrawals and anything that occurs after randomization. The result is a more accurate representation of the true effect of the treatment. If complete outcome data are available, it may also be possible to use a per protocol population which excludes those who did not follow through with the protocol. This article was authored by Sandeep K. Gupta.