The statistical and epidemiological analysis plan is usually structured to reflect the protocol and will address, where relevant, the following points:
8.1. Which confounders will be considered and how they will be defined
8.2. Adjustment for confounders in statistical models
8.3. Restriction in analysis
8.4. Matching, including PS matching
8.5. Self-controlled study designs
8.6. Statistical approach for any selection of a subset of confounders
8.7. Methods for assessing the level of confounding adjustment achieved
8.8. Sensitivity analyses for residual confounding
9.1. How missing data will be reported;
9.2. Methods of imputation;
9.3. Sensitivity analyses for handling missing data;
9.4. How censored data will be treated, with rationale.
10.1. Criteria for assessing fit;
10.2. Alternative models in the event of clear lack of fit.
11.1. Criteria, circumstances and possible drawbacks for performing an interim analysis and possible actions (including stopping rules) that can be taken on the basis of such an analysis
12.1. Description of target population;
12.2. Description of the analysis population if different, e.g. after PS matching or in IV analyses.
|10. Specific topics|
|Annex 1.||Guidance on conducting systematic revies and meta-analyses of completed comparative pharmacoepidemiological studies of safety outcomes|