The application of multilevel modelling to periodontal research data

Objective To explain the theory of multilevel modelling and demonstrate its application in the analysis of dental research data. Basic research design Multilevel modelling was introduced using dental data comprising four leve ls: repeated measurements at level-1, sites at level-2, teeth at level-3, a nd subjects at level-4. Variance components models (which have no explanato ry variables) were evaluated for all outcome measures. Explanatory variable s were added to the models with outcomes for both lifetime cumulative attac hment loss and pocket probing depth. Salient features of the multilevel mod els were discussed. Participants Research data were obtained from a longitu dinal survey of periodontal disease conducted on 100 white male trainee eng ineers aged between 16 and 20 years entering the apprentice training school at Royal Air Force Halton, England. Results The statistical methods reveal ed that periodontal measures demonstrate considerable variation at all leve ls of the multilevel structure. Models for lifetime cumulative attachment l oss and pocket probing depth illustrated that risk factors operated at more than one level. Supragingival calculus was a risk factor at the subject-le vel (subjects experiencing more sites with the condition had greater attach ment loss and greater pocketing) whilst there was apparently a protective e ffect occurring at the site (sites with the condition had less attachment l oss and less pocketing). Conclusions This study demonstrates that multileve l modelling is a more powerful research tool than single-level techniques f or the analysis of hierarchical dental data. Researchers using these techni ques are well equipped to analyse complex hierarchical data structures, suc h as those often found within dentistry.