The design and analysis of split-mouth studies: what statisticians and clinicians should know.

The split-mouth design is a popular design in oral health research. In the most common split-mouth study, each of two treatments are randomly assigned to either the right or left halves of the dentition. The attractiveness of the design is that it removes a lot of inter-individual variability from the estimates of the treatment effect. However, already about 20 years ago the pitfalls of the design have been reported in the oral health literature. Yet, many clinicians are not aware of the potential problems with the split-mouth design. Further, it is our experience that most statisticians are not even aware of the existence of this design. Since most of the critical remarks appeared in the oral health literature, we argue that it is necessary to introduce the split-mouth design to a statistical audience, so that both clinicians and statisticians clearly understand the advantages, limitations, statistical considerations, and implications of its use in clinical trials and advise them on its use in practice.