This is the first version.

Coordinating investigator (CI)

The coordinating investigator (CI) is the executive leader of the trial, and the Principal Investigator (PI) the investigator leading the trial at the individual trial site.

The CI is responsible for:

• Providing relevant information to the trial statistician (STAT) upon request.
• Keeping the STAT updated on the study and request advice on arising statistical issues.
• Initiating, reviewing and approving the Statistical Analysis Plan (SAP).
• Receiving and archiving the relevant documents in the Trial Master File (TMF).

Trial statistician (STAT)

The STAT is responsible for:

• Ensuring that the statistical activities described in this SOP are followed throughout the project, and relevant deviations are documented.
• Ensuring that the statistical parts, including design, is appropriate and properly described in the protocol.
• Ensuring that the statistical activities and analyses are validated as agreed, and have the required quality.
• Writing or filling in the SAP-
• Coding the statistical programs and performing the analyses
• If applicable, checking that the Data (Safety) Monitoring Committee (Board) (DMC/DSMB) charter is adequate.  
• Ensuring that the statistical activities reflect the requirements given in the Trial Protocol.

Quality control statistician (QC-STAT)

If Quality Control (QC) is performed, the Quality Control Statistician (QC-STAT) is responsible for:

• Supporting the STAT in the trial statistical activities.
• Controlling the quality of the statistical activities.
• Reviewing and approving the SAP.
• Providing assistance for statistical enquiries in case the STAT is unavailable.

DMC statistician (DMC-STAT)

If appointed, the Data Monitoring Committee Statistician (DMC-STAT) is responsible for:

• Coordinating input from STAT and DMC-STAT to the DMC charter.
• Providing the DMC with unblinded analyses and tabulations of interim results, based on code and templates provided by the STAT or Project Data Manager (PDM).
• Participating in DMC meetings and providing statistical interpretations of the report to the DMC.

Project data manger (PDM)

The Project Data Manager (PDM) is responsible for:

• Ensuring that the data delivered to the STAT is validated as agreed, and has the required quality.
• If applicable providing requested tables/input to DMC and statistical report.
• If feasible, facilitating randomization in the electronic Case Report Form (eCRF).

Statistical tasks

Protocol development

The STAT participates in the trial protocol development, while the CI has the main responsibility for the protocol. The statistically relevant parts in the protocol are:

• Trial design.
• Choice of outcomes/endpoints.
• Randomisation and blinding procedures.
• Sample size.
• Data management.
• Data and safety monitoring.
• Statistical methods and data analysis.

Preferably, the trial protocol should be based on a protocol template.

Data handling

Data handling consists of the following tasks:

• Creating the case report forms to ensure all relevant information with respect to the protocol is collected, i.e:
  • All elements involved in the derivation of the primary outcomes (could also include secondary/exploratory outcomes).
  • All demographic, baseline characteristics and other variables included in the primary analysis model.
  • All elements involved in the definition of the primary study population.
  • If applicable, all stratification variables if stratified randomisation is performed.
• Entering data.
• Validating data.
• Locking the database.

The PDM creates the CRF. The STAT performs a review of the CRF prior to a first finalisation and before release of any further updates during the study.

Randomisation

The STAT is responsible for preparing the randomization, and for writing all relevant documentation. The randomisation must be prepared using all relevant information, which includes e.g.:

• Number of treatment arms.
• Total number of subjects.
• Allocation ratio.
• Stratification factors.
• Blocking including block sizes.
• Degree of blinding.
• If available, template of allocation list.

The implementation of the randomisation should be performed, documented and archived such that the blinding of the trial is not compromised (Randomisation, blinding and unblinding - SOP). Depending on the how the randomisation is implemented, the documentation could include, but not restricted to:

• A document with the randomisation specifications.
• The program code.
• The seed used.
• Any log produced by running the code.
• The resulting randomisation list.

Data and safety monitoring

Statistical tasks for safety, possible efficacy monitoring are:

• Definition of the scope and tables required for the data and safety monitoring.
• Preparation of the code and the required tables for the monitoring.
• Supporting the medical monitors/CI in interpreting the statistical results.

The DMC charter must be written before the first participant is included.

Statistical analysis plan (SAP)

The SAP contains the detailed plan for the statistical analyses outlined in the protocol, including:

• Background of the statistical analyses.
• Approach of the statistical analyses.
• Justification of the statistical analyses.
• Detailed description of the statistical analyses.
• Statistical framework.
• Description of the planned report of the results.
• Statistical software used for the analyses.

The SAP contains at least all analyses for the main article but can be extended to more comprehensive analyses. Preferably, the SAP should be based on the statistical analysis plan template.

Statistical Programming

All statistical analyses must be coded in a suitable statistical programming language to guarantee the reproducibility of the results. Based on the SAP, the data and the security monitoring agreements, the tasks for statistical programming are:

• Generating or creating the code.
• Testing and quality checking of the code.
• Securing the availability of the code.
• Documenting the code.
• Creating a mock-up report using a fake random allocation to treatment not equal to the actual treatment allocation, regardless of whether the trial is open or blinded. This ensures unbiased decisions regarding statistical analysis.

Reporting

The statistical analyses must be reported in the manuscript to be published, including:

• Description of the statistical methods and analyses.
• Report of the results.
• Interpretation of the results.
• Quality control of all content related to statistics and analyses.
• Approval all content related to statistics and analyses.
• Answers to statistical queries or revision of post-hoc analyses in the review process.

Statistical Documentation

The Statistical Documentation for the clinical trial is an electronic archive documenting all statistical procedures, such as sample size calculations, randomisation, simulations, statistical analysis plan (SAP, including copies of literature references), statistical code programs and output.

Structure and content

Each trial Statistical Documentation is divided into different levels within the TMF:

Version control (and) maintenance

The Statistical Documentation should be filed as soon as they are created. Documents requiring approval and signature must be signed before filing. Version control should be established with the following specifications:

• Add the document date and version on the first page and in the footer.
• The first draft will have the version number 0.1, with subsequent versions 0.2, 0.3 etc.
• The first final version of the document will be numbered 1.0.
• Subsequent final revisions will be numbered 2.0, 3.0 etc.
• Intermittent drafts, similar to drafts before the first final revision, will be numbered 1.1, 1.2 etc.
• If relevant, a list of changes from previous major version will be added.
• Electronic documents will be stored and named according to:
  • (study short name) (document name) (version).
  • E.g. GREAT Statistical Analysis Plan v1.0.

Storage and archiving

The STAT will check that all documents are available in accordance with the Statistical Documentation at the end of the study and are sent to the CI for archiving in the TMF.

No deviation to this procedure is expected.

• Statistical Analysis Plan - Template
• Protocol - Template
• Data Monitoring Committee Charter - Template