The Fixed Dose Procedure (FDP) was first proposed in 1984 by the British Toxicology Society, as an alternative to the conventional LD50 test (OECD Test Guideline 401), for determining acute oral toxicity. The FDP used fewer animals and caused less suffering than the LD50 test, and provided information on acute toxicity which allowed substances to be classified according to the European Union hazard classification system. In 1992, the FDP was introduced as OECD Test Guideline 420. In 1999, as part of an initiative to phase out Test Guideline 401, a review of the FDP was undertaken. The aim of the review was to provide further reductions and refinements, and classification according to the criteria of the Globally Harmonised Hazard Classification and Labelling Scheme. The revised FDP was adopted by the OECD in 2001. This article concerns the development and revision of the FDP. It illustrates how statistical modelling and simulation can be used to increase the efficiency of a test procedure and reduce the number of animals needed for an in vivo validation of the procedure.