Overview

There are a few different pathways to statistically analyse the effect size investigated in randomized trials:

1. Per Protocol (PP) analysis
   Only patients with a complete data set and who actually received and complied with the allocated intervention/control are analyzed.
2. Complete Case (CC) analysis
   Only patients with a complete data set is included in the analysis irrespective if they received or complied to the allocated intervention/control.
3. Intention To Treat (ITT) analysis
   ITT means all patients randomized are included in the statistical analysis even if they did not receive the allocated treatment and they are also included even if they do not have a complete data set. In the latter case it means any missing data, if there is any, needs to be managed in some way and the most common options are: :
   a) Simple imputation methods such as “Last Observation Carried Forward (LOCF)”.
   b) Multiple imputation methods (MI).
   c) Mixed effects model analysis (MM).

ITT is the preferred analysis in all randomized trials. MI or MM are suitable to compensate for any missing data. However, MI or MM might be unsuitable if the available data are of poor quality . CC is likely a better choice if data is suspected of not being missing purely at random .

Per Protocol analysis (PP)

(Detta avsnitt är under konstruktion. Vi beklagar olägenheten.)

Complete Case analysis (CC)

(Detta avsnitt är under konstruktion. Vi beklagar olägenheten.)

Intention To Treat (ITT) analysis

(Detta avsnitt är under konstruktion. Vi beklagar olägenheten.)

References