In clinical trials the statistical report is the link between tables, listings and grahs and clinical study report. The latter is the final and official study closing documentation for review of Authorities. The Clinical Study Report (CSR) is created by Medical Writers and following very rules even in formatting or document structure.
The Statistical Report is generally prepared by the statistical team of a study. This summarises the whole study – including the medical background, the research goals, assessments and schedule. So far this description describes the Clinical Study Protocol. Where the statistical report is more: it also contains the main results of the study (generally 20-40% of the outputs of the statistical analysis) with a detailed explanation of the outcomes. Similarly important part of the document which shows the applied statistical methods. The analysis is always performed by the instructions of Statistical Analysis Plan (SAP), but SAP is approved before database closure, so some unexpected situations can emerge during application of SAP’s rules (e.g. unexpected distribution which makes a data transformation necessary, or a different missing value pattern from the expected one, which implies a minor change in the applied statistical tool. Reality can override the original analysis plans and it is allowed to modify them. But practically the Statistical Report is the only document where these types of changes can be accessable.
The European Medicines Agency let out two guideline. One for statistical considerations in clinical trials, the other about the formatting requirements of statistical reports. At Planimeter we follow these guidelines as far the actual Design, Protocol and SAP makes it possible.
ICH E9 statistical principles for clinical trials
Medical writers have to follow strict rules in writing of Clinical Study Report and so do the statisticians in preparation of Statistical Reports. The European Medicines Agencies (EMA) created a guideline containing some considerations applied in clinical trials. As they state ( https://www.ema.europa.eu/en/ich-e9-statistical-principles-clinical-trials ) :
“This document provides guidance on the design, conduct, analysis and evaluation of clinical trials of an investigational product in the context of its overall clinical development.”
The document was originally created in September 1998 and available here: https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e-9-statistical-principles-clinical-trials-step-5_en.pdf
An addendum /ICH E9 (R1) addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials/ was recently added in February 2020. That latest document can be download here: https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e9-r1-addendum-estimands-sensitivity-analysis-clinical-trials-guideline-statistical-principles_en.pdf .
Formatting requirements of Statistical Reports
ICH E3 Structure and content of clinical study reports
EMA also created a guidline for the structure and content of clinical study reports in July 1996.
This document aims to allow the compilation of a single core clinical study report acceptable to all regulatory authorities of the ICH regions.
The document can be avaiable on this link: https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e-3-structure-content-clinical-study-reports-step-5_en.pdf .