Mara Therese P. Evangelista MD, DPDS and Nick Huber
During the course of a clinical trial, large amounts of data are usually collected at different time points (i.e. at baseline and during follow-up visits). This results in the possibility of multiple statistical tests and various ways that the results can be reported. Some authors would naturally hope to show ‘interesting’ data, and this can lead to a tendency to hype the results. This must be resisted. It is of the utmost importance to report a balanced view of the results. This is why it is essential, before a trial starts, to have a protocol that states the primary and secondary endpoints and includes a pre-specified analysis plan.