Formal interim analysis

Note that this calculation must be undertaken on the blinded data to avoid any formal or informal treatment comparison. If such a comparison were to be made then there would be a price to pay in terms of the type I error. We will say much more about this in a later section dealing with interim analysis where the goal is to formally compare the treatment arms as the data accumulates. 

The trial was, in fact, stopped at the interim analysis due to futility the conditional power, was well below 30 per cent. In addition, even though the formal boundary for safety was not crossed, the trend was in the direction of excess deaths in the ancrod group. 

Now, with this groundwork finished, formal analysis can proceed. This does not mean that all caution can be thrown aside. The computer programs were tried out in the interim analyses or on test data sets, but the statistician should remain alert to the possibility of their errors and to the possibility of inconsistent data. Suspicious findings should be tracked back through the computer program and to the source of the original data. 

Team issues its first report which summarizes the major issues to do with the incident. The formal investigation team issues one or more interim reports as it progresses with its work. Lastly, the analysis team delivers the final report, containing both the root cause analysis, the findings, and suggested action items. 

The UK MoD were, as one might e q)ect, pioneers in the use of critical software and the development of static analysis tools to analyse the code (Malpas) as well as forays into formally proven hardware designs. In the Ught of finding defects in certain operational systems, dramatic changes to the supply chain as well as reductions in MoD scientific persotmel, they responded in 1989 with the publication of a new draft interim standard 00-55 (MoD 1989). This used expertise from the nuclear and aerospace industry, MoD and elsewhere to develop a market leading standard around the requirements for mathematically formally verified software and statistical testing. 

---