The International Conference on Harmonization (ICH) E9 guideline 'Statistical principles for clinical trials' was adopted by the Committee for Proprietary Medicinal Products in March 1998, and consequently is operational in Europe. It has also been adopted in the U.S.A. and Japan. The aim of this paper is to relate the problems encountered during a recent regulatory submission to those discussed in the ICH E9 guideline. Statistical principles discussed in the guideline, but not comprehensively addressed when the clinical development programme was initiated in the mid-1990s, will be reviewed. The impact of each issue on the approvability of the dossier will be discussed, together with recommendations on how to avoid such problems with other ongoing clinical development programmes. Copyright 2003 John Wiley & Sons, Ltd.